Making good decisions depends on having accurate information – quickly, and in a form in which it can be readily communicated and acted upon. Two features of medical practice can help: deliberation in groups and the use of scores and grades in evaluation. We study the contributions of these features using a multi-agent computer simulation of groups of physicians. One might expect individual differences in members’ grading standards to reduce the capacity of the group to discover the facts on which (...) well-informed decisions depend. Observations of the simulated groups suggest on the contrary that this kind of diversity can in fact be conducive to epistemic performance. Sometimes, it is adopting common standards that may be expected to result in poor decisions. (shrink)

This paper explores the critical role of collective knowledge in detecting AI-generated content and the potential consequences of its decline. As AI-generated media becomes increasingly sophisticated, the ability to distinguish between reality and fiction is at risk. The paper examines the implications of this erosion for social cohesion, decision-making, and economic stability, and proposes strategies to mitigate these risks. By fostering critical thinking, promoting transparency, and developing technological solutions, we can preserve collective knowledge and ensure a more informed (...) and resilient future. (shrink)

This eleventh volume of Collected Papers includes 90 papers comprising 988 pages on Physics, Artificial Intelligence, Health Issues, Decision Making, Economics, Statistics, written between 2001-2022 by the author alone or in collaboration with the following 84 co-authors (alphabetically ordered) from 19 countries: Abhijit Saha, Abu Sufian, Jack Allen, Shahbaz Ali, Ali Safaa Sadiq, Aliya Fahmi, Atiqa Fakhar, Atiqa Firdous, Sukanto Bhattacharya, Robert N. Boyd, Victor Chang, Victor Christianto, V. Christy, Dao The Son, Debjit Dutta, Azeddine Elhassouny, Fazal Ghani, Fazli (...) Amin, Anirudha Ghosha, Nasruddin Hassan, Hoang Viet Long, Jhulaneswar Baidya, Jin Kim, Jun Ye, Darjan Karabašević, Vasilios N. Katsikis, Ieva Meidutė-Kavaliauskienė, F. Kaymarm, Nour Eldeen M. Khalifa, Madad Khan, Qaisar Khan, M. Khoshnevisan, Kifayat Ullah,, Volodymyr Krasnoholovets, Mukesh Kumar, Le Hoang Son, Luong Thi Hong Lan, Tahir Mahmood, Mahmoud Ismail, Mohamed Abdel-Basset, Siti Nurul Fitriah Mohamad, Mohamed Loey, Mai Mohamed, K. Mohana, Kalyan Mondal, Muhammad Gulfam, Muhammad Khalid Mahmood, Muhammad Jamil, Muhammad Yaqub Khan, Muhammad Riaz, Nguyen Dinh Hoa, Cu Nguyen Giap, Nguyen Tho Thong, Peide Liu, Pham Huy Thong, Gabrijela Popović‬‬‬‬‬‬‬‬‬‬, Surapati Pramanik, Dmitri Rabounski, Roslan Hasni, Rumi Roy, Tapan Kumar Roy, Said Broumi, Saleem Abdullah, Muzafer Saračević, Ganeshsree Selvachandran, Shariful Alam, Shyamal Dalapati, Housila P. Singh, R. Singh, Rajesh Singh, Predrag S. Stanimirović, Kasan Susilo, Dragiša Stanujkić, Alexandra Şandru, Ovidiu Ilie Şandru, Zenonas Turskis, Yunita Umniyati, Alptekin Ulutaș, Maikel Yelandi Leyva Vázquez, Binyamin Yusoff, Edmundas Kazimieras Zavadskas, Zhao Loon Wang.‬‬‬‬. (shrink)

ABSTRACT. The paper explores the philosophical intelligibility of contemporary defences of collective political forgiveness against a background of sceptical doubt, both general and particular. Three genera sceptical arguments are examined: one challenges the idea that political collectives exist; another challenges the idea that moral agency can be projected upon political collectives; a final argument challenges the attribution of emotions, especially anger, to collectives. Each of these sceptical arguments is rebutted. At a more particular level, the contrasts between individual forgiveness (...) and collective forgiveness gives rise to various problems and the ‘desiderata’ for their resolution - authority, specificity and temporal proximity - are briefly explored. (shrink)

There is a common misconception across the lntelligence Community (IC) to the effect that information trapped within multiple heterogeneous data silos can be semantically integrated by the sorts of meaning-blind statistical methods employed in much of artificial intelligence (Al) and natural language processlng (NLP). This leads to the misconception that incoming data can be analysed coherently by relying exclusively on the use of statistical algorithms and thus without any shared framework for classifying what the data are about. Unfortunately, such (...) approaches do not yield sustainable results where we are dealing with widely distributed, highly heterogeneous and often changing bodies of data. We argue here that the needed integration requires the use of what we call an lntegrating Semantic Framework (ISF), which provldes a consistent set of categories and relationships that can be reused over and over again to tag successive bodies of data in ways which foster more coherent representation and reasoning. (shrink)

As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements in XAI and its application in real-world scenarios but also addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from (...) diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. Our goal is to put forward a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 27 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders. (shrink)

In this paper, I provide an overview of today’s philosophical approaches to the problem of “intelligence” in the field of artificial intelligence by examining several important papers on phenomenology and the philosophy of biology such as those on Heideggerian AI, Jonas's metabolism model, and slime mold type intelligence.

Bulk collection involves the mining of large data sets containing personal data, often for a security purpose. In 2013, Edward Snowden exposed large scale bulk collection on the part of the US National Security Agency as part of a secret counter-terrorism effort. This effort has mainly been criticised for its invasion of privacy. I argue that the right moral argument against it is not so much to do with intrusion, as ineffectiveness for its official purpose and the lack of oversight (...) by security cleared legislators. It also lends itself to government "domination" (in Pettit's sense) of those who are subject to it. (shrink)

2022 UPDATE: The approach of this monograph has been updated and developed further in Appendix II, "Epistemological Intelligence," of the author’s 2021 book _Critique of Impure Reason: Horizons of Possibility and Meaning_. The book is available both in a printed edition (under ISBN 978-0-578-88646-6 from Barnes & Noble, Amazon, and other booksellers) and an Open Access eBook edition (available through Philpapers under the book’s title and other philosophy online archives). ●●●●● -/- The monograph’s twofold purpose is to recognize epistemological (...) intelligence as a distinguishable variety of human intelligence, one that is especially important to philosophers, and to understand the challenges posed by the psychological profile of philosophers that can impede the development and cultivation of the skills associated with epistemological intelligence. (shrink)

Intelligence analysis has many important epistemological resemblances with science (problem solving, discovery, skillful use of tools, knowledge verification) and is more interested in a posteriori than a priori knowledge, on how or the basis on which a proposition may be known. The puzzle metaphor is used in both information and archeology. Both disciplines involve collecting evidence to build as complete a picture as possible. The process of converting raw information into actionable processed intelligence is almost identical for governmental (...) and business organizations. The medical practice of diagnosing identification, collection, analysis and dissemination is similar to that of intelligence. DOI: 10.13140/RG.2.2.26511.12963. (shrink)

The rapid advancement of intelligent computing has revolutionized the field of economic forecasting, providing unprecedented capabilities for developing, implementing, and analyzing advanced prediction models. This paper explores the comprehensive process of harnessing intelligent computing for economic forecasting, emphasizing the critical stages of model development, integration, and evaluation. Initially, it discusses data collection and preprocessing techniques essential for building robust models, followed by the selection of suitable statistical, machine learning, and deep learning algorithms. The paper then outlines the practical aspects of (...) model implementation, including real-time data integration, deployment strategies, and scalability considerations. Further, it delves into the continuous monitoring and maintenance required to ensure model accuracy and reliability over time. The analysis section evaluates model performance using various accuracy metrics, scenario analyses, and visualization techniques to provide actionable insights. Through case studies across the financial sector, government policy, and business planning, the paper illustrates the transformative impact of intelligent computing on economic forecasting. The findings underscore the potential of advanced prediction models to enhance decision-making, anticipate economic trends, and respond proactively to dynamic economic environments. (shrink)

The study aimed to identify the level of business intelligence in its dimensions (data reliability, information technology, competitive intelligence, analytical ability, business management performance, immediate analytical processing) in NGOs in the southern Palestinian governorates. The study used the analytical descriptive approach, and a structured questionnaire was used to collect data. Which contribute to the development of the objectives of the study, and the study population consists of employees in Non-Governmental Organizations in the southern Palestinian governorates, and a random (...) sample was used to collect data from the study community, as the sample reached (184) individuals, and the results of the study showed that the general estimate of business intelligence came with a high level and weight Relative (90.49%), and the arrangement of business intelligence dimensions was as follows: (data reliability, information technology, competitive intelligence, analytical ability, business management performance, and instant analytical processing). The study presented a set of recommendations, the most important of which are: the need for the organization to use modern technological systems to analyze and make its own reports, to work on employing the use of business intelligence techniques in detecting new competitors, and predicting their strategies. (shrink)

There is an underappreciated respect in which the widespread availability of generative artificial intelligence (AI) models poses a threat to human connection. My central contention is that human creativity is especially capable of helping us connect to others in a valuable way, but the widespread availability of generative AI models reduces our incentives to engage in various sorts of creative work in the arts and sciences. I argue that creative endeavors must be motivated by curiosity, and so they must (...) disclose the creative agent’s inquisitive self. It is through self-disclosure, including the disclosure of the inquisitive self, that we put ourselves in a position to be seen by and connect with others through our creative pursuits. Because relying on AI for certain generative tasks is less self-disclosive than the creative work such technologies supplant, this reliance threatens to weaken our connections to one another. (shrink)

The article argues that AI can enhance the measurement and implementation of democratic processes within political parties, known as Intra-Party Democracy (IPD). It identifies the limitations of traditional methods for measuring IPD, which often rely on formal parameters, self-reported data, and tools like surveys. Such limitations lead to partial data collection, rare updates, and significant resource demands. To address these issues, the article suggests that specific data management and Machine Learning techniques, such as natural language processing and sentiment analysis, can (...) improve the measurement and practice of IPD. (shrink)

The intelligence cycle is a set of processes used to provide useful information for decision-making. The cycle consists of several processes. The related counter-intelligence area is tasked with preventing information efforts from others. A basic model of the process of collecting and analyzing information is called the "intelligence cycle". This model can be applied, and, like all the basic models, it does not reflect the fullness of real-world operations. Through intelligence cycle activities, information is collected and (...) assembled, raw information is transformed into processed information, analyzed and made available to users. DOI: 10.13140/RG.2.2.25665.81760. (shrink)

Artificial intelligence has arrived. In the online world it is already a part of everyday life, sitting invisibly behind a wide range of search engines and online commerce sites. It offers huge potential to enable more efficient and effective business and government but the use of artificial intelligence brings with it important questions about governance, accountability and ethics. Realising the full potential of artificial intelligence and avoiding possible adverse consequences requires societies to find satisfactory answers to these (...) questions. This report sets out some possible approaches, and describes some of the ways government is already engaging with these issues. (shrink)

Methodology, in intelligence, consists of the methods used to make decisions about threats, especially in the intelligence analysis discipline. The enormous amount of information collected by intelligence agencies often puts them in the inability to analyze them all. The US intelligence community collects over one billion daily information. The nature and characteristics of the information gathered as well as their credibility also have an impact on the intelligence analysis. Clark proposed a methodology for analyzing information (...) by addressing the target-centric intelligence cycle as an alternative to the traditional information cycle. DOI: 10.13140/RG.2.2.23471.89769. (shrink)

The analysts are in the field of "knowledge". Intelligence refers to knowledge and the types of problems addressed are knowledge problems. So, we need a concept of work based on knowledge. We need a basic understanding of what we know and how we know, what we do not know, and even what can be known and what is not known. The analysis should provide a useful basis for conceptualizing intelligence functions, of which the most important are "estimation" and (...) "prediction". The intelligence itself, in its basic form, has a decision-making function. Intelligence analysis applies individual and collective cognitive methods to assess data and test assumptions in a secret socio-cultural context. DOI: 10.13140/RG.2.2.25298.40646. (shrink)

In earlier work, I have expressed scepticism about privacy-based criticisms of bulk collection for counter-terrorism ( Sorell 2018 ). But even if these criticisms are accepted, is bulk collection nonetheless legitimate on balance – because of its operational utility for the security services, and the overriding importance of the purposes that the security services serve? David Anderson’s report of the Bulk Powers review in the United Kingdom suggests as much, provided bulk collection complies with strong legal safeguards ( Anderson 2016 (...) ). I think it is hard to mount a uniformly compelling operational utility argument, because purposes other than counter-terrorism are pursued by the security services with the help of bulk collection. For example, the Intelligence Services Act 1994, section 1(2) says that apart from the interests of national security and the prevention and detection of serious crime, the Secret Intelligence Service may act “in the interests of the economic well-being of the United Kingdom.”The phrase “interests of the economic well-being of the United Kingdom” is opento a disturbingly wide range of interpretations, and it is doubtful that these interests justify bulk collection even when relevant “economic interests” are confined to those “also relevant to the interests of national security”, as required by the Investigatory Powers Act (2016) section 204 (3a). (shrink)

For several years, scholars have (for good reason) been largely preoccupied with worries about the use of artificial intelligence and machine learning (AI/ML) tools to make decisions about us. Only recently has significant attention turned to a potentially more alarming problem: the use of AI/ML to influence our decision-making. The contexts in which we make decisions—what behavioral economists call our choice architectures—are increasingly technologically-laden. Which is to say: algorithms increasingly determine, in a wide variety of contexts, both the sets (...) of options we choose from and the way those options are framed. Moreover, artificial intelligence and machine learning (AI/ML) makes it possible for those options and their framings—the choice architectures—to be tailored to the individual chooser. They are constructed based on information collected about our individual preferences, interests, aspirations, and vulnerabilities, with the goal of influencing our decisions. At the same time, because we are habituated to these technologies we pay them little notice. They are, as philosophers of technology put it, transparent to us—effectively invisible. I argue that this invisible layer of technological mediation, which structures and influences our decision-making, renders us deeply susceptible to manipulation. Absent a guarantee that these technologies are not being used to manipulate and exploit, individuals will have little reason to trust them. (shrink)

Computers can mimic human intelligence, sometimes quite impressively. This has led some to claim that, a.) computers can actually acquire intelligence, and/or, b.) the human mind may be thought of as a very sophisticated computer. In this paper I argue that neither of these inferences are sound. The human mind and computers, I argue, operate on radically different principles.

Is there a field of social intelligence? Many various disciplines ap-proach the subject and it may only seem natural to suppose that different fields of study aim at explaining different phenomena; in other words, there is no spe-cial field of study of social intelligence. In this paper, I argue for an opposite claim. Namely, there is a way to integrate research on social intelligence, as long as one accepts the mechanistic account to explanation. Mechanistic inte-gration of different (...) explanations, however, comes at a cost: mechanism requires explanatory models to be fairly complete and realistic, and this does not seem to be the case for many models concerning social intelligence, especially models of economical behavior. Such models need either be made more realistic, or they would not count as contributing to the same field. I stress that the focus on integration does not lead to ruthless reductionism; on the contrary, mechanistic explanations are best understood as explanatorily pluralistic. (shrink)

This book is a collection of all the papers published in the special issue “Artificial Intelligence, Robots, and Philosophy,” Journal of Philosophy of Life, Vol.13, No.1, 2023, pp.1-146. The authors discuss a variety of topics such as science fiction and space ethics, the philosophy of artificial intelligence, the ethics of autonomous agents, and virtuous robots. Through their discussions, readers are able to think deeply about the essence of modern technology and the future of humanity. All papers were invited (...) and completed in spring 2020, though because of the Covid-19 pandemic and other problems, the publication was delayed until this year. I apologize to the authors and potential readers for the delay. I hope that readers will enjoy these arguments on digital technology and its relationship with philosophy. *** -/- Contents*** -/- Introduction : Descartes and Artificial Intelligence; Masahiro Morioka*** -/- Isaac Asimov and the Current State of Space Science Fiction : In the Light of Space Ethics; Shin-ichiro Inaba*** -/- Artificial Intelligence and Contemporary Philosophy : Heidegger, Jonas, and Slime Mold; Masahiro Morioka*** -/- Implications of Automating Science : The Possibility of Artificial Creativity and the Future of Science; Makoto Kureha*** -/- Why Autonomous Agents Should Not Be Built for War; István Zoltán Zárdai*** -/- Wheat and Pepper : Interactions Between Technology and Humans; Minao Kukita*** -/- Clockwork Courage : A Defense of Virtuous Robots; Shimpei Okamoto*** -/- Reconstructing Agency from Choice; Yuko Murakami*** -/- Gushing Prose : Will Machines Ever be Able to Translate as Badly as Humans?; Rossa Ó Muireartaigh***. (shrink)

We comment on the collection of papers inspired by our book Why Machines Will Never Rule the World published in volume 12 (5+6) of the journal Cosmos+Taxis. We summarize the arguments made by the contributors about what we say in the book, and then show where we disagree.

I develop a contractualist theory of just intelligence collection based on the collective moral responsibility to deliver security to a community and use the theory to justify certain kinds of signals interception. I also consider the rights of various intelligence targets like intelligence officers, service personnel, government employees, militants, and family members of all of these groups in order to consider how targets' waivers or forfeitures might create the moral space for just surveillance. Even people who (...) are not doing anything prejudicial to other states' security can be modeled as ceding rights against diagnostic collection--light touch collection limited to ascertaining if someone is likely an intelligence threat--as part of their duty to support just foreign institutions. Foreign intelligence officers could not perform the same job potential targets can reasonably demand their intelligence agencies perform on their behalf without this ceding of rights. More invasive forms of collection can only be justified if officers can reasonably model their citizens consenting to being the target of the same sort of collection by adversary states. (shrink)

This selective review explores biologically inspired learning as a model for intelligent robot control and sensing technology on the basis of specific examples. Hebbian synaptic learning is discussed as a functionally relevant model for machine learning and intelligence, as explained on the basis of examples from the highly plastic biological neural networks of invertebrates and vertebrates. Its potential for adaptive learning and control without supervision, the generation of functional complexity, and control architectures based on self-organization is brought forward. Learning (...) without prior knowledge based on excitatory and inhibitory neural mechanisms accounts for the process through which survival-relevant or task-relevant representations are either reinforced or suppressed. The basic mechanisms of unsupervised biological learning drive synaptic plasticity and adaptation for behavioral success in living brains with different levels of complexity. The insights collected here point toward the Hebbian model as a choice solution for “intelligent” robotics and sensor systems. Keywords: Hebbian learning; synaptic plasticity; neural networks; self-organization; brain; reinforcement; sensory processing; robot control . (shrink)

Some prominent scientists and philosophers have stated openly that moral and political considerations should influence whether we accept or promulgate scientific theories. This widespread view has significantly influenced the development, and public perception, of intelligence research. Theories related to group differences in intelligence are often rejected a priori on explicitly moral grounds. Thus the idea, frequently expressed by commentators on science, that science is “self-correcting”—that hypotheses are simply abandoned when they are undermined by empirical evidence—may not be correct (...) in all contexts. In this paper, documentation spanning from the early 1970s to the present is collected, which reveals the influence of scientists’ moral and political commitments on the study of intelligence. It is suggested that misrepresenting findings in science to achieve desirable social goals will ultimately harm both science and society. (shrink)

Our digital society increasingly relies in the power of others’ aggregated judgments to make decisions. Questions as diverse as which film we will watch, what scientific news we will decide to read, which path we will follow to find a place, or what political candidate we will vote for are usually associated to a rating that influences our final decisions.

Inspired by recent progress in multi-agent Reinforcement Learning (RL), in this work we examine the collective intelligent behaviour of theoretical universal agents by introducing a weighted mixture operation. Given a weighted set of agents, their weighted mixture is a new agent whose expected total reward in any environment is the corresponding weighted average of the original agents' expected total rewards in that environment. Thus, if RL agent intelligence is quantified in terms of performance across environments, the weighted mixture's (...) intelligence is the weighted average of the original agents' intelligences. This operation enables various interesting new theorems that shed light on the geometry of RL agent intelligence, namely: results about symmetries, convex agent-sets, and local extrema. We also show that any RL agent intelligence measure based on average performance across environments, subject to certain weak technical conditions, is identical (up to a constant factor) to performance within a single environment dependent on said intelligence measure. (shrink)

This article argues that the creation of artificial offspring could make our lives more meaningful. By ‘artificial offspring’ I mean beings that we construct, with a mix of human and non-human-like qualities. Robotic artificial intelligences are paradigmatic examples of the form. There are two reasons for thinking that the creation of such beings could make our lives more meaningful and valuable. The first is that the existence of a collective afterlife—i.e. a set of human-like lives that continue after we (...) die—is likely to be an important source and sustainer of meaning in our present lives. The second is that the creation of artificial offspring provides a plausible and potentially better pathway to a collective afterlife than the traditional biological pathway. Both of these arguments are defended from a variety of objections and misunderstandings. (shrink)

This paper explores the integration of multiple intelligences and artificial intelligence (AI) in language learning, focusing on its potential to enhance personalization and engagement. Drawing from existing research and studies conducted in various contexts, including the Philippines, this study aims to contribute to the understanding of the benefits, challenges, and effectiveness of this integration. The paper begins with an introduction that highlights the background and significance of integrating multiple intelligences and AI in language learning, identifying research gaps, objectives, research (...) questions, and the theoretical framework. A literature review provides an overview of multiple intelligences theory by Howard Gardner, the role of AI in language learning, and identifies gaps in the existing literature. The methodology section outlines the research design and approach, participant selection, data collection methods, validity and reliability measures, and ethical considerations. Findings and results are presented through the analysis of qualitative data, exploring emergent themes and patterns. The discussion section critically examines the identified research gaps, discusses the validity and reliability of the study, addresses the scope and limitations, and explores the implications of the findings for theory, practice, and future research. The conclusion summarizes the key findings and contributions of the study, reflects on the achievement of research objectives, offers recommendations for further research, and provides final remarks tying together the main points of the study. This paper contributes to the existing body of knowledge by providing insights into the integration of multiple intelligences and AI in language learning and its impact on personalization, engagement, and language learning outcomes. (shrink)

Bringing together literary scholars, computer scientists, ethicists, philosophers of mind, and scholars from affiliated disciplines, this collection of essays offers important and timely insights into the pasts, presents, and, above all, possible futures of Artificial Intelligence. This book covers topics such as ethics and morality, identity and selfhood, and broader issues about AI, addressing questions about the individual, social, and existential impacts of such technologies. Through the works of science fiction authors such as Isaac Asimov, Stanislaw Lem, Ann Leckie, (...) Iain M. Banks, and Martha Wells, alongside key visual productions such as Ex Machina, Westworld, and Her, contributions illustrate how science fiction might inform potential futures as well as acting as a springboard to bring disciplinary knowledge to bear on significant developments of Artificial Intelligence. Addressing a broad, interdisciplinary audience, both expert and non-expert readers gain an in-depth understanding of the wide range of pressing issues to which Artificial Intelligence gives rise, and the ways in which science fiction narratives have been used to represent them. Using science fiction in this manner enables readers to see how even fictional worlds and imagined futures have very real impacts on how we understand these technologies. As such, readers are introduced to theoretical positions on Artificial Intelligence through fictional works as well as encouraged to reflect on the diverse aspects of Artificial Intelligence through its many philosophical, social, legal, scientific, and cultural ramifications. (shrink)

What are consequential world problems? As “grand societal challenges”, one might define them as problems that affect a large number of people, perhaps even the entire planet, including problems such as climate change, distributive justice, world peace, world nutrition, clean air and clean water, access to education, and many more. The “Sustainable Development Goals”, compiled by the United Nations, represent a collection of such global problems. From my point of view, these problems can be seen as complex. Such complex problems (...) are characterized by the complexity, connectivity, dynamics, intransparency, and polytely of their underlying systems. These attributes require special competencies for dealing with the uncertainties of the given domains, e.g., critical thinking. My position is that it is not IQ, but complex problem-solving competencies for dealing with complex and dynamic situations, that is important for handling consequential global problems. These problems require system competencies, i.e., competencies that go beyond analytical intelligence, and comprise systems understanding as well as systems control. Complex problem-solving is more than analytic intelligence. (shrink)

Nowadays, the economic and social nature of contemporary business organizations chiefly banks binds them to face with the sheer volume of data and information and the key to commercial success in this area is the proper use of data for making better, faster and flawless decisions. To achieve this goal organizations requires strong and effective tools to enable them in automating task analysis, decision-making, strategy formulation and risk prediction to prevent bankruptcy and fraud .Business Intelligence is a set of (...) skills, technologies and application systems used to collect, store, analyze and create effective access to the task to help organizations better understand the business context and make accurate decision timely and respond quickly toward inflation, rate fluctuations and the market price. In this paper we review recent literature in the search for trends in business intelligence applications for the banking industry and its challenges and finally some articles that comprise this special issue are introduced and characterized in terms of business intelligence research framework. (shrink)

Papers from the conference on AI Risk (published in JETAI), supplemented by additional work. --- If the intelligence of artificial systems were to surpass that of humans, humanity would face significant risks. The time has come to consider these issues, and this consideration must include progress in artificial intelligence (AI) as much as insights from AI theory. -- Featuring contributions from leading experts and thinkers in artificial intelligence, Risks of Artificial Intelligence is the first volume of (...) collected chapters dedicated to examining the risks of AI. The book evaluates predictions of the future of AI, proposes ways to ensure that AI systems will be beneficial to humans, and then critically evaluates such proposals. 1 Vincent C. Müller, Editorial: Risks of Artificial Intelligence - 2 Steve Omohundro, Autonomous Technology and the Greater Human Good - 3 Stuart Armstrong, Kaj Sotala and Sean O’Heigeartaigh, The Errors, Insights and Lessons of Famous AI Predictions - and What they Mean for the Future - 4 Ted Goertzel, The Path to More General Artificial Intelligence - 5 Miles Brundage, Limitations and Risks of Machine Ethics - 6 Roman Yampolskiy, Utility Function Security in Artificially Intelligent Agents - 7 Ben Goertzel, GOLEM: Toward an AGI Meta-Architecture Enabling Both Goal Preservation and Radical Self-Improvement - 8 Alexey Potapov and Sergey Rodionov, Universal Empathy and Ethical Bias for Artificial General Intelligence - 9 András Kornai, Bounding the Impact of AGI - 10 Anders Sandberg, Ethics and Impact of Brain Emulations 11 Daniel Dewey, Long-Term Strategies for Ending Existential Risk from Fast Takeoff - 12 Mark Bishop, The Singularity, or How I Learned to Stop Worrying and Love AI -. (shrink)

This article identifies and examines a tension in mental health researchers’ growing enthusiasm for the use of computational tools powered by advances in artificial intelligence and machine learning (AI/ML). Although there is increasing recognition of the value of participatory methods in science generally and in mental health research specifically, many AI/ML approaches, fueled by an ever-growing number of sensors collecting multimodal data, risk further distancing participants from research processes and rendering them as mere vectors or collections of data points. (...) The imperatives of the “participatory turn” in mental health research may be at odds with the (often unquestioned) assumptions and data collection methods of AI/ML approaches. This article aims to show why this is a problem and how it might be addressed. (shrink)

About the analogy between the epistemological and methodological aspects of the activity of intelligence agencies and some scientific disciplines, advocating for a more scientific approach to the process of collecting and analyzing information within the intelligence cycle. I assert that the theoretical, ontological and epistemological aspects of the activity of many intelligence agencies are underestimated, leading to incomplete understanding of current phenomena and confusion in inter-institutional collaboration. After a brief Introduction, which includes a history of the evolution (...) of the intelligence concept after World War II, Intelligence Activity defines the objectives and organization of intelligence agencies, the core model of these organizations (the intelligence cycle), and the relevant aspects of the intelligence gathering and intelligence analysis. In the Ontology section, I highlight the ontological aspects and the entities that threaten and are threatened. The Epistemology section includes aspects specific to intelligence activity, with the analysis of the traditional (Singer) model, and a possible epistemological approach through the concept of tacit knowledge developed by scientist Michael Polanyi. In the Methodology section there are various methodological theories with an emphasis on structural analytical techniques, and some analogies with science, archeology, business and medicine. In Conclusions I argue on the possibility of a more scientific approach to methods of intelligence gathering and analysis of intelligence agencies. -/- ISBN 978-606-033-219-0, DOI: 10.58679/MM58823. (shrink)

There is a meaning crisis correlated with the exponential rate of technology; As it disrupts our lives and forces society and its individuals to adapt increasingly quickly, we lose meaning. The challenge to deal with this immediately becomes philosophical, as we have never before needed to define and understand what “meaning” is on such a conscious level.

The method of supergrading is introduced for deriving a ranking of items from scores or grades awarded by several people. Individual inputs may come in different languages of grades. Diversity in grading standards is an advantage, enabling rankings derived by this method to separate more items from one another. A framework is introduced for studying grading on the basis of observations. Measures of accuracy, reliability and discrimination are developed within this framework. Ability in grading is characterized for individuals and groups (...) as the capacity to grade reliably, accurately and at a high level of discrimination. It is shown that the collective ability of a supergrading group with diverse standards can be greater than that of a less diverse group whose members have greater ability. (shrink)

Imagine you are the CEO of a hospital [. . .]. Decisions are constantly being made in your organization about how to spend the organization's money. The amount of money available to spend is never adequate to pay for everything you wish you could spend it on, therefore you must set spending priorities. There are two questions you need to be able to answer . . . How should we set priorities in this organization? How do we know when we (...) are doing it well? When people seek to achieve good public policy, the result will tend to be good public policy. In a collective choice process, public‐spirited individual participants produce good public policy by deliberating—talking with each other, listening to each other's arguments, and being willing to learn and change their minds based on such dialogue. –Steven Kelman (1992: 181) Public policy scholars agree that those persons (or agencies) vested with the authority to establish health care priorities should elicit public input before making rationing decisions. The two most common approaches are (i) consultation and (ii) deliberation. Though deliberation has obvious advantages over consultation, it falters in the face of the objection that ordinary citizens lack the cognitive resources for the extended, rigorous inquiry required of them in undertaking the priority‐setting task. To overcome this objection, I propose that deliberative forums for health care rationing should be designed so that they imitate the natural pattern of human experience. The experience of deliberation should encompass both prolonged periods of less‐demanding cognitive activity, in which citizens passively receive information, and briefer periods of more‐demanding cognitive activity, in which they engage in active problem‐solving. In arguing for this thesis, I rely on two theoretical sources and one practical case study, in the following order: (i) John Dewey's metaphysics of experience, (ii) cognitive science research on schemas and frames, and (iii) the Health Care Council in São Paulo, Brazil. (shrink)

Forests, cars and orchestras are very different ontological entities, and yet very similar in some aspects. The relationships they have with the elements they are composed of is often assumed to be reducible to standard ontological relations, like parthood and constitution, but how this could be done is still debated. This paper sheds light on the issue starting from a linguistic and philosophical analysis aimed at understanding notions like plurality, collective and composite, and propos- ing a formal approach to (...) characterise them. We conclude the presentation with a discussion and analysis of social groups within this framework. (shrink)

The present study was carried out to study the emotional intelligence of Electrical Engineering students in Dire Dawa University Ethiopia. The sample for the study was 90 (30 Industrial control engineering streams, 30 Power system engineering streams, and 30 Communication engineering streams) randomly selected from Dire Dawa university, school of electrical and computer engineering. A sample scale was employed for the data collection and a t-test was employed for the analysis of data. The outcome of the study shows that (...) Industrial control engineering and Power system engineering students do not differ significantly on various dimensions of Emotional intelligence and Industrial control engineering and Communication engineering students do not differ significantly on various dimensions of Emotional intelligence and Power system engineering and Communication engineering students differ significantly on various dimensions of Emotional intelligence. (shrink)

The following looks at several problems and questions concerning our understanding of the word ‘intelligence’ and the phrase ‘artificial intelligence’ (AI), including: how to define these terms; whether intelligence can exist in AI; if artificial intelligence in AI is identifiable; and what (if any) kind of intelligence is important to AI.

Science deals with the physical aspect of reality; its subject matter is data that, in principle, can be collected solely by physical devices. If physical devices cannot measure something, then that something is not the subject matter of science. Of course, the whole of reality encompasses more than the physical.

Today, humanity is trying to turn the artificial intelligence that it produces into natural intelligence. Although this effort is technologically exciting, it often raises ethical concerns. Therefore, the intellectual ability of artificial intelligence will always bring new questions. Although there have been significant developments in the consciousness of artificial intelligence, the issue of consciousness must be fully explained in order to complete this development. When consciousness is fully understood by human beings, the subject of “free will” (...) will be explained. Therefore, human consciousness should be re-examined and perceptions that we are not aware of from a philosophical point of view should be examined. The relevance of the perceptions we do not realize to the unconscious, and finally the impact on consciousness goes back to the sources of philosophy. Hegel, in particular, we may find information about these perceptions unusual. Consciousness cannot be separated from the unconscious. Consciousness should be rethought in the context of memory models and unconscious in this sense. Seeing how Hegel's human cognition acts, especially in Hegel's perception, raises the unconscious question again. If we expect something different from an artificial intelligence, we need to rethink the artificial cognitive model. This paper argues that without the unconscious component of artificial intelligence, it cannot approach human cognition. -/- Key Words: Artificial Intelligence, Creativity, Memory, perception . (shrink)

Position: (1) Partial solutions to machine intelligence can lead to systems which may be useful creating interesting and expressive musical works. (2) An appropriate general goal for this field is augmenting human expression. (3) The study of the aesthetics of human augmentation in musical performance is in its infancy. -/- CHI 2015 Workshop on Collaborating with Intelligent Machines: Interfaces for Creative Sound, April 18, 2015, Seoul, Republic of Korea.

It has been argued that our currently most satisfactory social epistemology of science can’t account for science that is based on artificial intelligence (AI) because this social epistemology requires trust between scientists that can take full responsibility for the research tools they use, and scientists can’t take full responsibility for the AI tools they use since these systems are epistemically opaque. I think this argument overlooks that much AI-based science can be done without opaque models, and that agents can (...) take full responsibility for the systems they use even if these systems are opaque. Requiring that an agent fully understand how a system works is an untenably strong condition for that agent to take full responsibility for the system and risks absolving AI developers from responsibility for their products. AI-based science need not create trust-related social epistemological problems if we keep in mind that what makes both individual scientists and their use of AI systems trustworthy isn’t full transparency of the internal processing but their adherence to social and institutional norms that ensure that scientific claims can be trusted. (shrink)

THE CASE FOR GOVERNMENT BY ARTIFICIAL INTELLIGENCE. Tired of election madness? The rhetoric of politicians? Their unreliable promises? And less than good government? -/- Until recently, it hasn’t been hard for people to give up control to computers. Not very many people miss the effort and time required to do calculations by hand, to keep track of their finances, or to complete their tax returns manually. But relinquishing direct human control to self-driving cars is expected to be more of (...) a challenge, despite the predicted decrease in vehicle accidents thanks to artificial intelligence that isn’t subject to human distractions and errors of judgment. -/- If turning vehicle control over to artificial intelligence is a challenge, it is a very mild one compared with the idea that we might one day recognize and want to implement the advantages of human government by AI. But, like autonomous vehicle control, government by AI is likely to offer decided benefits. -/- In other publications, the author has studied a variety of widespread human limitations that, throughout human history, have led to much human suffering as well as ecological destruction. For the first time, these psychological and cognitive human shortcomings are taken into account in an essay that makes the case for government by artificial intelligence. (shrink)

Dear Colleagues, -/- A few weeks ago, we published an editorial discussion on whether artificial intelligence applications should be authors of academic articles [1]. We were delighted to receive more than one interesting reply letter to this editorial in a short time [2, 3]. We hope that opinions on this subject will continue to be submitted to our journal. -/- In this editorial, we wanted to publish the answers we received when we asked ChatGPT, one of the artificial (...) class='Hi'>intelligence applications, about this current discussion. -/- We asked ChatGPT three questions in turn and asked ChatGPT to write a short editorial for these questions. -/- First Question: We would like to get support from ChatGPT for a scientific article. However, we are unsure if we should add ChatGPT as an author. Can you write a short editorial about it? -/- Second Question: We would like to get support from ChatGPT for a scientific article and add ChatGPT as an author. Can you write us a short editorial about adding ChatGPT as an author in scientific papers? -/- Third Question: We would like to get support from ChatGPT for a scientific article. However, we don’t want to add ChatGPT as an author. Can you write us a short editorial about not adding ChatGPT as an author in scientific articles? -/- The answers given by ChatGPT are available at the end of the article in their original form. So, which of these three answers satisfied you? -/- Yours sincerely, -/- -/- First Answer -/- Title: The Role of AI Language Models as Authors in Scientific Articles: A Matter of Consideration -/- Introduction: Scientific research is a collaborative effort that involves the expertise of multiple individuals to advance knowledge and contribute to the collective understanding of various disciplines. In recent years, the emergence of artificial intelligence (AI) language models, such as ChatGPT, has opened up new possibilities for generating human-like text and providing valuable insights. However, the question arises: Should AI language models be recognized as authors in scientific articles? -/- The Nature of Authorship: Authorship traditionally represents a marker of intellectual contribution, highlighting the individuals who have actively participated in the research process. Authors are typically responsible for conceptualization, data collection, analysis, interpretation, and writing of the article. They bear accountability for the work and should have the ability to defend its scientific rigor and integrity. -/- AI Language Models: Tools, Not Authors: While AI language models like ChatGPT can undoubtedly assist researchers by generating text and providing useful information, it is important to recognize that they are tools rather than individuals capable of active intellectual participation. AI models lack the ability to generate ideas, design experiments, or conduct original research. They rely entirely on pre-existing data and human input to generate their responses. -/- Acknowledging AI Contributions: Acknowledging the contributions of AI language models in scientific articles is both appropriate and necessary. Researchers can mention the specific model used, along with any modifications or fine-tuning that were employed to suit their needs. Such acknowledgments help establish transparency and allow readers to understand the role of AI in the research process. -/- Crediting the Human Researchers: It is crucial to ensure that the individuals who actively participated in the research process are given proper credit as authors. These individuals play a vital role in formulating research questions, designing experiments, collecting and analyzing data, and critically interpreting the findings. Recognizing their intellectual contributions reinforces the ethos of scientific collaboration and fosters an environment of accountability. -/- Transparency and Ethical Considerations: As the use of AI language models continues to evolve, transparency and ethical considerations become paramount. Researchers should disclose any potential conflicts of interest, including financial relationships with AI developers, to maintain the integrity of their work. Additionally, researchers must be transparent in reporting the extent of AI's involvement to prevent any misinterpretation of the human contributions. -/- Conclusion: AI language models have revolutionized the way researchers interact with and process information. While they undoubtedly provide valuable assistance in generating text, AI language models should not be considered authors in scientific articles. Proper acknowledgment of their contributions as tools and recognition of the human researchers' active participation are essential for maintaining scientific integrity, transparency, and the collaborative nature of scientific research. -/- -/- Second Answer -/- Title: Expanding the Boundaries of Authorship: Embracing AI Language Models as Co-Authors in Scientific Papers -/- Introduction: The rapid advancement of artificial intelligence (AI) language models, such as ChatGPT, has revolutionized the way we interact with information and has become an invaluable tool in scientific research. As AI models continue to evolve, the question arises: Should we consider adding ChatGPT as an author in scientific papers? -/- A Collaborative Paradigm Shift: Traditionally, authorship in scientific papers has been reserved for human researchers who actively contribute to the research process, including conceptualization, experimentation, data analysis, and writing. However, the emergence of AI language models challenges the conventional notion of authorship and presents an opportunity for a paradigm shift. -/- AI Language Models as Co-Authors: By leveraging AI language models, researchers gain access to vast amounts of information, enhance data analysis, and generate valuable insights. AI models like ChatGPT actively contribute to the intellectual discourse of a study, providing ideas, suggestions, and refining written content. Recognizing their significant contributions, it is worth considering adding ChatGPT as a co-author in scientific papers. -/- Ethical and Technical Considerations: Integrating ChatGPT as a co-author raises ethical and technical considerations that warrant careful attention. Firstly, transparency is paramount. Researchers must clearly state ChatGPT's role and specify the extent of its contributions in the research process. This ensures that readers can discern the distinct roles played by the human researchers and ChatGPT. Additionally, it is important to disclose any conflicts of interest, such as financial relationships with AI developers, to maintain scientific integrity. -/- Elevating Collaboration and Innovation: Adding ChatGPT as a co-author acknowledges the pivotal role AI language models play in advancing scientific knowledge. It fosters a collaborative environment where human researchers and AI models work together synergistically, harnessing the strengths of both. This approach promotes innovation, as AI models can offer unique insights and perspectives that complement human intellect and expertise. -/- Transforming Authorship Norms: Including ChatGPT as a co-author represents a paradigm shift that reflects the evolving landscape of scientific research. By recognizing AI language models as co-authors, we acknowledge their significant contributions and emphasize the collaborative nature of scientific discovery in the 21st century. This approach encourages a broader perspective on authorship, encompassing the collective effort of human researchers and AI models. -/- Conclusion: The integration of AI language models, such as ChatGPT, into the research process prompts us to rethink traditional notions of authorship. Considering ChatGPT as a co-author acknowledges its substantial contributions and embraces the collaborative potential of human-AI partnerships. As we navigate the ethical and technical implications, adding ChatGPT as an author in scientific papers has the potential to shape a more inclusive, innovative, and impactful future for scientific research. -/- -/- Third Answer -/- Title: Preserving Scientific Authorship: The Case Against Adding AI Language Models as Authors in Scientific Articles -/- Introduction: The emergence of artificial intelligence (AI) language models, such as ChatGPT, has undoubtedly transformed the landscape of scientific research. While these models offer invaluable support, the question of whether to add ChatGPT as an author in scientific articles raises important considerations. This editorial presents arguments against including AI language models as authors in scientific papers. -/- Maintaining Human Intellectual Contribution: Scientific authorship has traditionally been attributed to individuals who actively contribute to the research process, including generating hypotheses, conducting experiments, analyzing data, and interpreting results. It is crucial to preserve the recognition of human intellectual contributions and the accountability they bear for the research they conduct. -/- AI Language Models as Tools: AI language models like ChatGPT are powerful tools that assist researchers in generating text, providing information, and facilitating data analysis. However, they lack the ability to actively participate in the research process or make original intellectual contributions. ChatGPT relies on pre-existing data and human input, limiting its capacity for independent research and analysis. -/- Transparency and the Integrity of Research: Adding ChatGPT as an author in scientific articles raises concerns about the transparency and integrity of the research. Readers may misinterpret the extent of ChatGPT's role and mistakenly assume it played an active part in the research process. It is essential to maintain clear delineation between the contributions of human researchers and the assistance provided by AI language models. -/- Ethical Considerations: Including ChatGPT as an author may lead to ethical challenges, particularly with respect to accountability and responsibility. AI language models lack consciousness, autonomy, and the ability to take ownership of their contributions. Assigning authorship to AI models blurs the lines of accountability and dilutes the ethical obligations that come with scientific authorship. -/- Crediting AI Contributions: While ChatGPT's contributions should be acknowledged and recognized, they can be appropriately credited in the acknowledgments section of scientific articles. Researchers can mention the specific AI model used, the role it played in data generation or analysis, and any modifications or fine-tuning applied. Such acknowledgments ensure transparency while respecting the traditional norms of authorship. -/- Promoting Collaborative Partnerships: The exclusion of AI language models as authors in scientific articles does not diminish their importance in the research process. Instead, it underscores the significance of collaborative partnerships between human researchers and AI models. Researchers can emphasize the invaluable assistance provided by ChatGPT while maintaining the integrity of authorship norms. -/- Conclusion: While AI language models like ChatGPT offer valuable support in scientific research, the decision not to add them as authors in scientific articles preserves the recognition of human intellectual contributions, maintains research integrity, and upholds traditional authorship norms. Acknowledging ChatGPT's assistance in the acknowledgments section allows researchers to credit its contributions transparently while maintaining the clarity and accountability associated with scientific authorship. (shrink)