Machine Learning

Issues of reliability are claiming center-stage in the epistemology of machine learning. This paper unifies different branches in the literature and points to promising research directions, whilst also providing an accessible introduction to key concepts in statistics and machine learning---as far as they are concerned with reliability.

Modern life sciences research is increasingly relying on artificial intelligence (AI) approaches to model biological systems, primarily centered around the use of machine learning (ML) models. Although ML is undeniably useful for identifying patterns in large, complex data sets, its widespread application in biological sciences represents a significant deviation from traditional methods of scientific inquiry. As such, the interplay between these models and scientific understanding in biology is a topic with important implications for the future of scientific research, yet it (...) is a subject that has received little attention. Here, we draw from an epistemological toolkit to contextualize recent applications of ML in biological sciences under modern philosophical theories of understanding, identifying general principles that can guide the design and application of ML systems to model biological phenomena and advance scientific knowledge. We propose that conceptions of scientific understanding as information compression, qualitative intelligibility, and dependency relation modelling provide a useful framework for interpreting ML-mediated understanding of biological systems. Through a detailed analysis of two key application areas of ML in modern biological research – protein structure prediction and single cell RNA-sequencing – we explore how these features have thus far enabled ML systems to advance scientific understanding of their target phenomena, how they may guide the development of future ML models, and the key obstacles that remain in preventing ML from achieving its potential as a tool for biological discovery. Consideration of the epistemological features of ML applications in biology will improve the prospects of these methods to solve important problems and advance scientific understanding of living systems. (shrink)

In Philosophy and Technology 36, David Watson discusses the epistemological and metaphysical implications of unsupervised machine learning (ML) algorithms. Watson is sympathetic to the epistemological comparison of unsupervised clustering, abstraction and generative algorithms to human cognition and sceptical about ML’s mechanisms having ontological implications. His epistemological commitments are that we learn to identify “natural kinds through clustering algorithms”, “essential properties via abstraction algorithms”, and “unrealized possibilities via generative models” “or something very much like them.” The same issue contains a commentary (...) on Watson’s paper in which Tom Sterkenburg fiercely opposes the epistemological claim that clustering algorithms can identify natural kinds. Sterkenburg argues there’s nothing about clustering arguments themselves that enables natural kind identification. What’s at stake in the Watson-Sterkenburg debate is whether it is possible for clustering algorithms to identify natural kinds and whether they underly human identification of natural kinds. My contribution to the Watson-Sterkenburg debate is twofold. First, I argue Sterkenburg’s criticism of Watson’s claim is too severe because it denies any clustering algorithm to identify any natural kind. Secondly, I argue Watson’s reply overestimates both clustering algorithms’ and humans’ access to natural kinds and his claim has to be restricted accordingly to ‘We identify kinds via clustering algorithms, or something very much like them’. (shrink)

Bayesian classifiers perform well when each of the features is completely independent of the other which is not always valid in real world applications. The aim of this study is to implement and compare the performances of each variant of the Bayesian classifier (Multinomial, Bernoulli, and Gaussian) on anomaly detection in network intrusion, and to investigate whether there is any association between each variant’s assumption and their performance. Our investigation showed that each variant of the Bayesian algorithm blindly follows its (...) assumption regardless of feature property, and that the assumption is the single most important factor that influences their accuracy. Experimental results show that Bernoulli has accuracy of 69.9% test (71% train), Multinomial has accuracy of 31.2% test (31.2% train), while Gaussian has an accuracy of 81.69% test (82.84% train). Going deeper, we investigated and found that each Naïve Bayes variants performances and accuracy is largely due to each classifier assumption, Gaussian classifier performed best on anomaly detection due to its assumption that features follow normal distributions which are continuous, while multinomial classifier have a dismal performance as it simply assumes discreet and multinomial distribution. (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)

Despite its centrality in the philosophy of cognitive science, there has been little prior philosophical work engaging with the notion of representation in contemporary NLP practice. This paper attempts to fill that lacuna: drawing on ideas from cognitive science, I introduce a framework for evaluating the representational claims made about components of neural NLP models, proposing three criteria with which to evaluate whether a component of a model represents a property and operationalising these criteria using probing classifiers, a popular analysis (...) technique in NLP (and deep learning more broadly). The project of operationalising a philosophically-informed notion of representation should be of interest to both philosophers of science and NLP practitioners. It affords philosophers a novel testing-ground for claims about the nature of representation, and helps NLPers organise the large literature on probing experiments, suggesting novel avenues for empirical research. (shrink)

This work demonstrates the implementation and use of an encoder-decoder model to perform a many-to-many mapping of video data to text captions. The many-to-many mapping occurs via an input temporal sequence of video frames to an output sequence of words to form a caption sentence. Data preprocessing, model construction, and model training are discussed. Caption correctness is evaluated using 2-gram BLEU scores across the different splits of the dataset. Specific examples of output captions were shown to demonstrate model generality over (...) the video temporal dimension. Predicted captions were shown to generalize over video action, even in instances where the video scene changed dramatically. Model architecture changes are discussed to improve sentence grammar and correctness. (shrink)

The irrational exuberance associated with contemporary artificial intelligence (AI) reminds me of Charles Dickens: "it was the age of foolishness, it was the epoch of belief" (cf. Nature Editorial, 2016; to get a feel for the vanity fair that is AI, see Mitchell and Krakauer, 2023; Stilgoe, 2023). It is particularly distressing—feels like yet another rerun of Seinfeld, which is all about nothing (pun intended); we have seen it in the 60s and again in the 90s. AI might have had (...) an inauspicious beginning, which may very well be the original sin, and our current predicament is the attendant divine condemnation. Being unable to stand it, however divine it may be, without further ado, I get to the genesis (instead of getting lost in the here-and-now of this or that so-called breakthrough of AI). Here's my unvarnished critique! (shrink)

The present paper looks at one of the most thorough articles on the intelligence of GPT, research conducted by engineers at Microsoft. Although there is a great deal of value in their work, I will argue that, for familiar philosophical reasons, their methodology, ‘Black-box Interpretability’ is wrongheaded. But there is a better way. There is an exciting and emerging discipline of ‘Inner Interpretability’ (also sometimes called ‘White-box Interpretability’) that aims to uncover the internal activations and weights of models in order (...) to understand what they represent and the algorithms they implement. In my view, a crucial mistake in Black-box Interpretability is the failure to appreciate that how processes are carried out matters when it comes to intelligence and understanding. I can’t pretend to have a full story that provides both necessary and sufficient conditions for being intelligent, but I do think that Inner Interpretability dovetails nicely with plausible philosophical views of what intelligence requires. So the conclusion is modest, but the important point in my view is seeing how to get the research on the right track. Towards the end of the paper, I will show how some of the philosophical concepts can be used to further refine how Inner Interpretability is approached, so the paper helps draw out a profitable, future two-way exchange between Philosophers and Computer Scientists. (shrink)

We propose the concepts of philomatics and psychomatics as hybrid combinations of philosophy and psychology with mathematics. We explain four motivations for this combination which are fulfilling the desire of analytical philosophy, proposing science of philosophy, justifying mathematical algorithms by philosophy, and abstraction in both philosophy and mathematics. We enumerate various examples for philomatics and psychomatics, some of which are explained in more depth. The first example is the analysis of relation between the context principle, semantic holism, and the usage (...) theory of meaning with the attention mechanism in mathematics. The other example is on the relations of Plato's theory of forms in philosophy with the holographic principle in string theory, object-oriented programming, and machine learning. Finally, the relation between Wittgenstein's family resemblance and clustering in mathematics is explained. This paper opens the door of research for combining philosophy and psychology with mathematics. (shrink)

The use of machine learning, or “artificial intelligence” (AI) in medicine is widespread and growing. In this paper, I focus on a specific proposed clinical application of AI: using models to predict incapacitated patients’ treatment preferences. Drawing on results from machine learning, I argue this proposal faces a special moral problem. Machine learning researchers owe us assurance on this front before experimental research can proceed. In my conclusion I connect this concern to broader issues in AI safety.

We propose a quantum curiosity algorithm as a means to implement quantum thinking into AI, and we illustrate 5 new quantum curiosity types. We then introduce 6 new hybrid quantum curiosity types combining animal and plant curiosity elements with biomimicry beyond human sensing. We then introduce 4 specialized quantum curiosity types, which incorporate quantum thinking into coding frameworks to radically transform problem-solving and discovery in science, medicine, and systems analysis. We conclude with a forecasting of the future of quantum thinking (...) in AI and illustrate an example of how to apply the new curiosity types: General Collaborative Networks. (shrink)

Current methods of operationalizing concepts of misinformation in machine learning are often problematic given idiosyncrasies in their success conditions compared to other models employed in the natural and social sciences. The intrinsic value-ladenness of misinformation and the dynamic relationship between citizens' and social scientists' concepts of misinformation jointly suggest that both the construct legitimacy and the construct validity of these models needs to be assessed via more democratic criteria than has previously been recognized.

Recent advances in natural language processing have given rise to a new kind of AI architecture: the language agent. By repeatedly calling an LLM to perform a variety of cognitive tasks, language agents are able to function autonomously to pursue goals specified in natural language and stored in a human-readable format. Because of their architecture, language agents exhibit behavior that is predictable according to the laws of folk psychology: they function as though they have desires and beliefs, and then make (...) and update plans to pursue their desires given their beliefs. We argue that the rise of language agents significantly reduces the probability of an existential catastrophe due to loss of control over an AGI. This is because the probability of such an existential catastrophe is proportional to the difficulty of aligning AGI systems, and language agents significantly reduce that difficulty. In particular, language agents help to resolve three important issues related to aligning AIs: reward misspecification, goal misgeneralization, and uninterpretability. (shrink)

Some physicians, in their care of patients at risk of misusing opioids, use machine learning (ML)-based prediction drug monitoring programmes (PDMPs) to guide their decision making in the prescription of opioids. This can cause a conflict: a PDMP Score can indicate a patient is at a high risk of opioid abuse while a patient expressly reports oppositely. The prescriber is then left to balance the credibility and trust of the patient with the PDMP Score. Pozzi1 argues that a prescriber who (...) downgrades the credibility of a patient’s testimony based on a low PDMP Score is epistemically and morally unjustified and contributes to a form of testimonial injustice. This results in patients being silenced, excluded from decision-making processes and subjected to structural injustices. Additionally, the use of ML systems in medical practices raises concerns about perpetuating existing inequalities, overestimating their capabilities and displacing human authority. However, almost the very same critiques apply to human-based systems. Formalisation, ML systems included, should instead be viewed positively,2 and precisely as a powerful means to begin eroding these and other problems in ethically sensitive domains. In this case, the epistemic virtues of formalisation include promoting transparency, consistency and replicability in decision making. Rigorous ML systems can also help ensure that models …. (shrink)

Definition of the problem The umbrella term “explicability” refers to the reduction of opacity of artificial intelligence (AI) systems. These efforts are challenging for medical AI applications because higher accuracy often comes at the cost of increased opacity. This entails ethical tensions because physicians and patients desire to trace how results are produced without compromising the performance of AI systems. The centrality of explicability within the informed consent process for medical AI systems compels an ethical reflection on the trade-offs. Which (...) levels of explicability are needed to obtain informed consent when utilizing medical AI? Arguments We proceed in five steps: First, we map the terms commonly associated with explicability as described in the ethics and computer science literature, i.e., disclosure, intelligibility, interpretability, and explainability. Second, we conduct a conceptual analysis of the ethical requirements for explicability when it comes to informed consent. Third, we distinguish hurdles for explicability in terms of epistemic and explanatory opacity. Fourth, this then allows to conclude the level of explicability physicians must reach and what patients can expect. In a final step, we show how the identified levels of explicability can technically be met from the perspective of computer science. Throughout our work, we take diagnostic AI systems in radiology as an example. Conclusion We determined four levels of explicability that need to be distinguished for ethically defensible informed consent processes and showed how developers of medical AI can technically meet these requirements. (shrink)

If Large Language Models can make real scientific contributions, then they can genuinely use language, be systematically wrong, and be held responsible for their errors. AI models which can make scientific contributions thereby meet the criteria for scientific authorship.

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 paper presents a new trilemma with respect to resolving the control and alignment problems in machine ethics. Section 1 outlines three possible types of artificial moral agents (AMAs): (1) 'Inhuman AMAs' programmed to learn or execute moral rules or principles without understanding them in anything like the way that we do; (2) 'Better-Human AMAs' programmed to learn, execute, and understand moral rules or principles somewhat like we do, but correcting for various sources of human moral error; and (3) 'Human-Like (...) AMAs' programmed to understand and apply moral values in broadly the same way that we do, with a human-like moral psychology. Sections 2–4 then argue that each type of AMA generates unique control and alignment problems that have not been fully appreciated. Section 2 argues that Inhuman AMAs are likely to behave in inhumane ways that pose serious existential risks. Section 3 then contends that Better-Human AMAs run a serious risk of magnifying some sources of human moral error by reducing or eliminating others. Section 4 then argues that Human-Like AMAs would not only likely reproduce human moral failures, but also plausibly be highly intelligent, conscious beings with interests and wills of their own who should therefore be entitled to similar moral rights and freedoms as us. This generates what I call the New Control Problem: ensuring that humans and Human-Like AMAs exert a morally appropriate amount of control over each other. Finally, Section 5 argues that resolving the New Control Problem would, at a minimum, plausibly require ensuring what Hume and Rawls term ‘circumstances of justice’ between humans and Human-Like AMAs. But, I argue, there are grounds for thinking this will be profoundly difficult to achieve. I thus conclude on a skeptical note. Different approaches to developing ‘safe, ethical AI’ generate subtly different control and alignment problems that we do not currently know how to adequately resolve, and which may or may not be ultimately surmountable. (shrink)

We argue that machine learning algorithms can inflict microaggressions on members of marginalized groups and that recognizing these harms as instances of microaggressions is key to effectively addressing the problem. The concept of microaggression is also illuminated by being studied in algorithmic contexts. We contribute to the microaggression literature by expanding the category of environmental microaggressions and highlighting the unique issues of moral responsibility that arise when we focus on this category. We theorize two kinds of algorithmic microaggression, stereotyping and (...) erasure microaggressions, and argue that corporations are responsible for the microaggressions their algorithms create. As a case study, we look at the problems faced by Google’s autocomplete prediction and at the insufficiency of their solutions. The case study of autocomplete demonstrates our core claim that microaggressions constitute a distinct form of algorithmic bias and that identifying them as such allows us to avoid seeming solutions that recreate the same kinds of harms. Google has a responsibility to make information freely available, without exposing users to degradation. To fulfill its duties to marginalized groups, Google must abandon the fiction of neutral prediction and instead embrace the liberatory power of suggestion. (shrink)

We can illustrate the phenomenon of model-induced escape by examining the phenomenon of spam filters. Spam filter A is, we can assume, very effective at blocking spam. Indeed it is so effective that it motivates the authors of spam to invent new types of spam that will beat the filters of spam filter A. -/- An example of this phenomenon in the realm of philosophy is illustrated in the work of Nyíri on Wittgenstein's political beliefs. Nyíri writes a paper demonstrating (...) convincingly that there are strong signals of a conservative strain of thought in the writings of Wittgenstein. This has initially a tiny effect; but then a more significant effect sets in as the authors of Wittgenstein secondary literature, consciously or unconsciously, draw attention to features of Wittgenstein which cast the conservatism thesis in a negative light. This is an example of what I call model-induced escape: the Nyíri model of Wittgenstein initiates a process which undermines the Nyíri model of Wittgenstein. -/- Wittgenstein, as obiectum philosophiae, is reduced to a constantly mutating set of interpretations of a certain body of work. -/- Perhaps this is what makes philosophy so problematic when viewed from the perspective of results, or in other words of signs of progress commonly accepted across the discipline. There are just too many ways of inducing escape from any given putative discovery; too many dimensions along which an interpretative or definitional arms race can be triggered. (shrink)

This is the proceedings of the "1st Turkish Conference on AI and ANNs," K. Oflazer, V. Akman, H. A. Guvenir, and U. Halici (editors). The conference was held at Bilkent University, Bilkent, Ankara on 25-26 June 1992. -/- Language of contributions: English and Turkish.

Should we fear a future in which the already tricky world of academic publishing is increasingly crowded out by super-intelligent artificial general intelligence (AGI) systems writing papers on phenomenology and ethics? What are the chances that AGI advances to a stage where a human philosophy instructor is similarly removed from the equation? If Jobst Landgrebe and Barry Smith are correct, we have nothing to fear.

We present a game mechanic called pseudo-visibility for games inhabited by non-player characters (NPCs) driven by reinforcement learning (RL). NPCs are incentivized to pretend they cannot see pseudo-visible players: the training environment simulates an NPC to determine how the NPC would act if the pseudo-visible player were invisible, and penalizes the NPC for acting differently. NPCs are thereby trained to selectively ignore pseudo-visible players, except when they judge that the reaction penalty is an acceptable tradeoff (e.g., a guard might accept (...) the penalty in order to protect a treasure because losing the treasure would hurt even more). We describe an RL agent transformation which allows RL agents that would not otherwise do so to perform some limited self-reflection to learn the training environments in question. (shrink)

The desirable gambles framework offers the most comprehensive foundations for the theory of lower pre- visions, which in turn affords the most general ac- count of imprecise probabilities. Nevertheless, for all its generality, the theory of lower previsions rests on the notion of linear utility. This commitment to linearity is clearest in the coherence axioms for sets of desirable gambles. This paper considers two routes to relaxing this commitment. The first preserves the additive structure of the desirable gambles framework and (...) the machinery for coherent inference but detaches the interpretation of desirability from the multiplicative scale invariance axiom. The second strays from the additive combination axiom to accommodate repeated gambles that return rewards by a non-stationary processes that is not necessarily additive. Unlike the first approach, which is a conservative amendment to the desirable gambles framework, the second is a rad- ical departure. Yet, common to both is a method for describing rewards called discounted utility. (shrink)

Ever since the era of internet had ushered in cloud computing, there had been increase in the demand for the unlimited data available through cloud computing for data analysis, pattern recognition and technology advancement. With this also bring the problem of scalability, efficiency and security threat. This research paper focuses on how data can be dynamically mine in real time for pattern detection in a secure cloud computing environment using combination of decision tree algorithm and Random Forest over a restful (...) Application Programming Interface (API). We are able to successfully Implement data mining on cloud computing bypassing or avoiding direct interaction with data warehouse and without any terminal involve by using combination of IBM Cloud storage facility, Amazing Web Service, Application Programming Interface and Window service along with a decision tree and Random Forest algorithm for our classifier. We were able to successfully bypass direct connection with the data warehouse and cloud terminal with 94% accuracy in our model. (shrink)

Unless and until our society recognizes cyber bullying for what it is, the suffering of thousands of silent victims will continue.” ~ Anna Maria Chavez. There had been series of research on cyber bullying which are unable to provide reliable solution to cyber bullying. In this research work, we were able to provide a permanent solution to this by developing a model capable of detecting and intercepting bullying incoming and outgoing messages with 92% accuracy. We also developed a chatbot automation (...) messaging system to test our model leading to the development of Artificial Intelligence powered anti-cyber bullying system using machine learning algorithm of Multinomial Naïve Bayes (MNB) and optimized linear Support Vector Machine(SVM). Our model is able to detect and intercept bullying outgoing and incoming bullying messages and take immediate action. (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)

Le déficit d’explicabilité des techniques d’apprentissage machine (AM) pose des problèmes opérationnels, juridiques et éthiques. Un des principaux objectifs de notre projet est de fournir des explications éthiques des sorties générées par une application fondée sur de l’AM, considérée comme une boîte noire. La première étape de ce projet, présentée dans cet article, consiste à montrer que la validation de ces boîtes noires diffère épistémologiquement de celle mise en place dans le cadre d’une modélisation mathéma- tique et causale d’un phénomène (...) physique. La différence majeure est qu’une méthode d’AM ne prétend pas représenter une causalité entre les paramètres d’entrées et ceux de sortie. Après avoir proposé une clarification et une adaptation des notions d’inter- prétabilité et d’explicabilité telles qu’on les rencontre dans la littérature déjà abondante sur le sujet, nous montrons dans cet article l’intérêt de mettre en œuvre les distinctions épistémologiques entre les différentes fonctions épistémiques d’un modèle, d’une part, et entre la fonction épistémique et l’usage d’un modèle, d’autre part. Enfin, la dernière partie de cet article présente nos travaux en cours sur l’évaluation d’une explication, qui peut être plus persuasive qu’informative, ce qui peut ainsi causer des problèmes d’ordre éthique. (shrink)

Under what conditions does machine learning (ML) model opacity inhibit the possibility of explaining and understanding phenomena? In this article, I argue that nonepistemic values give shape to the ML opacity problem even if we keep researcher interests fixed. Treating ML models as an instance of doing model-based science to explain and understand phenomena reveals that there is (i) an external opacity problem, where the presence of inductive risk imposes higher standards on externally validating models, and (ii) an internal opacity (...) problem, where greater inductive risk demands a higher level of transparency regarding the inferences the model makes. (shrink)

In a recent article, Erasmus, Brunet, and Fisher (2021) argue that Artificial Neural Networks (ANNs) are explainable. They survey four influential accounts of explanation: the Deductive-Nomological model, the Inductive-Statistical model, the Causal-Mechanical model, and the New-Mechanist model. They argue that, on each of these accounts, the features that make something an explanation is invariant with regard to the complexity of the explanans and the explanandum. Therefore, they conclude, the complexity of ANNs (and other Machine Learning models) does not make them (...) less explainable. In this reply, it is argued that Erasmus et al. left out one influential account of explanation from their discussion: the Unificationist model. It is argued that, on the Unificationist model, the features that makes something an explanation is sensitive to complexity. Therefore, on the Unificationist model, ANNs (and other Machine Learning models) are not explainable. It is emphasized that Erasmus et al.’s general strategy is correct. The literature on explainable Artificial Intelligence can benefit by drawing from philosophical accounts of explanation. However, philosophical accounts of explanation do not settle the problem of whether ANNs are explainable because they do not unanimously declare that explanation is invariant with regard to complexity. (shrink)

Simple idealized models seem to provide more understanding than opaque, complex, and hyper-realistic models. However, an increasing number of scientists are going in the opposite direction by utilizing opaque machine learning models to make predictions and draw inferences, suggesting that scientists are opting for models that have less potential for understanding. Are scientists trading understanding for some other epistemic or pragmatic good when they choose a machine learning model? Or are the assumptions behind why minimal models provide understanding misguided? In (...) this paper, using the case of deep neural networks, I argue that it is not the complexity or black box nature of a model that limits how much understanding the model provides. Instead, it is a lack of scientific and empirical evidence supporting the link that connects a model to the target phenomenon that primarily prohibits understanding. (shrink)

We introduce and discuss a knowledge-driven distillation approach to explaining black-box models by means of two kinds of interpretable models. The first is perceptron (or threshold) connectives, which enrich knowledge representation languages such as Description Logics with linear operators that serve as a bridge between statistical learning and logical reasoning. The second is Trepan Reloaded, an ap- proach that builds post-hoc explanations of black-box classifiers in the form of decision trees enhanced by domain knowledge. Our aim is, firstly, to target (...) a model-agnostic distillation approach exemplified with these two frameworks, secondly, to study how these two frameworks interact on a theoretical level, and, thirdly, to investigate use-cases in ML and AI in a comparative manner. Specifically, we envision that user-studies will help determine human understandability of explanations generated using these two frameworks. (shrink)

We discuss the role of perceptron (or threshold) connectives in the context of Description Logic, and in particular their possible use as a bridge between statistical learning of models from data and logical reasoning over knowledge bases. We prove that such connectives can be added to the language of most forms of Description Logic without increasing the complexity of the corresponding inference problem. We show, with a practical example over the Gene Ontology, how even simple instances of perceptron connectives are (...) expressive enough to represent learned, complex concepts derived from real use cases. This opens up the possibility to import concepts learnt from data into existing ontologies. (shrink)

In their paper 'Reward is enough', Silver et al conjecture that the creation of sufficiently good reinforcement learning (RL) agents is a path to artificial general intelligence (AGI). We consider one aspect of intelligence Silver et al did not consider in their paper, namely, that aspect of intelligence involved in designing RL agents. If that is within human reach, then it should also be within AGI's reach. This raises the question: is there an RL environment which incentivises RL agents to (...) design RL agents? (shrink)

It has been argued that ethical frameworks for data science often fail to foster ethical behavior, and they can be difficult to implement due to their vague and ambiguous nature. In order to overcome these limitations of current ethical frameworks, we propose to integrate the analysis of the connections between technical choices and sociocultural factors into the data science process, and show how these connections have consequences for what data subjects can do, accomplish, and be. Using healthcare as an example, (...) attention to sociocultural conversion factors relevant to health can help in navigating technical choices that require broader considerations of the sociotechnical system, such as metric tradeoffs in model validation, resulting in better ethical and technical choices. This approach promotes awareness of the ethical dimension of technical choices by data scientists and others, and that can foster the cultivation of 'ethical skills' as integral to data science. (shrink)

Epistemic closure refers to the assumption that humans are able to recognize what entails or contradicts what they believe and know, or more accurately, that humans’ epistemic states are closed under logical inferences. Epistemic closure is part of a larger theory of mind ability, which is arguably crucial for downstream NLU tasks, such as inference, QA and conversation. In this project, we introduce a new automatically constructed natural language inference dataset that tests inferences related to epistemic closure. We test and (...) further fine tune the model RoBERTa-large-mnli on the new dataset, with limited positive results. (shrink)

We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent's hypothetical behavior. Since good performance usually requires paying attention to whatever things the environment's outputs are based on, we argue that for an agent to achieve on-average good performance across many such extended environments, it is necessary for the agent to self-reflect. Thus weighted-average performance over the space of all suitably well-behaved extended environments could be considered a (...) way of measuring how self-reflective an agent is. We give examples of extended environments and introduce a simple transformation which experimentally seems to increase some standard RL agents' performance in a certain type of extended environment. (shrink)

Typically, fair machine learning research focuses on a single decision maker and assumes that the underlying population is stationary. However, many of the critical domains motivating this work are characterized by competitive marketplaces with many decision makers. Realistically, we might expect only a subset of them to adopt any non-compulsory fairness-conscious policy, a situation that political philosophers call partial compliance. This possibility raises important questions: how does partial compliance and the consequent strategic behavior of decision subjects affect the allocation outcomes? (...) If k% of employers were to voluntarily adopt a fairness-promoting intervention, should we expect k% progress (in aggregate) towards the benefits of universal adoption, or will the dynamics of partial compliance wash out the hoped-for benefits? How might adopting a global (versus local) perspective impact the conclusions of an auditor? In this paper, we propose a simple model of an employment market, leveraging simulation as a tool to explore the impact of both interaction effects and incentive effects on outcomes and auditing metrics. Our key findings are that at equilibrium: (1) partial compliance by k% of employers can result in far less than proportional (k%) progress towards the full compliance outcomes; (2) the gap is more severe when fair employers match global (vs local) statistics; (3) choices of local vs global statistics can paint dramatically different pictures of the performance vis-a-vis fairness desiderata of compliant versus non-compliant employers; (4) partial compliance based on local parity measures can induce extreme segregation. Finally, we discuss implications for auditors and insights concerning the design of regulatory frameworks. (shrink)

Computational complexity is a discipline of computer science and mathematics which classifies computational problems depending on their inherent difficulty, i.e. categorizes algorithms according to their performance, and relates these classes to each other. P problems are a class of computational problems that can be solved in polynomial time using a deterministic Turing machine while solutions to NP problems can be verified in polynomial time, but we still do not know whether they can be solved in polynomial time as well. A (...) solution for the so-called NP-complete problems will also be a solution for any other such problems. Its artificial-intelligence analogue is the class of AI-complete problems, for which a complete mathematical formalization still does not exist. In this chapter we will focus on analysing computational classes to better understand possible formalizations of AI-complete problems, and to see whether a universal algorithm, such as a Turing test, could exist for all AI-complete problems. In order to better observe how modern computer science tries to deal with computational complexity issues, we present several different deep-learning strategies involving optimization methods to see that the inability to exactly solve a problem from a higher order computational class does not mean there is not a satisfactory solution using state-of-the-art machine-learning techniques. Such methods are compared to philosophical issues and psychological research regarding human abilities of solving analogous NP-complete problems, to fortify the claim that we do not need to have an exact and correct way of solving AI-complete problems to nevertheless possibly achieve the notion of strong AI. (shrink)

Popular culture continues fuelling public imagination with things, human and non-human, that we might beco-me or confront. Besides robots, other significant tropes in popular fiction that generated images include non-human humans and cyborgs, wired into his-torically varying sociocultural realities. Robots and artificial intelligence are re-defining the natural order and its hierar-chical structure. This is not surprising, as natural order is always in flux, shaped by new scientific discoveries, especially the reading of the genetic code, that reveal and redefine relationships between (...) life forms. However, for the first time, a new, artificial, species is being introduced into the existing diagrams, and, for the first time, it appears to hybridise the anthro-pocentric natural world order. (shrink)

Coronary Heart Disease (CHD) is one of the leading causes of death nowadays. Prediction of the disease at an early stage is crucial for many health care providers to protect their patients and save lives and costly hospitalization resources. The use of machine learning in the prediction of serious disease events using routine medical records has been successful in recent years. In this paper, a comparative analysis of different machine learning techniques that can accurately predict the occurrence of CHD events (...) from clinical data was performed. Four machine learning classifiers, namely Logistic Regression, Support Vector Machine (SVM), K- Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) Neural Networks were identified and applied to a dataset of 462 medical instances and 9 features as well as the class feature from the South African Heart Disease data retrieved from the KEEL repository. The dataset consists of 302 records of healthy patients and 160 records of patients who suffer from CHD. In order to handle the imbalanced classification problem, the K-means algorithm along with Synthetic Minority Oversampling TEchnique (SMOTE) was used in this study. The empirical results of applying the four machine learning classifiers on the oversampled dataset have been very promising. The results reported using different evaluation metrics showed that SVM has achieved the highest overall prediction performance. (shrink)

Biomarker-based predictive tests for subjectively asymptomatic Alzheimer’s disease (AD) are utilized in research today. Novel applications of artificial intelligence (AI) promise to predict the onset of AD several years in advance without determining biomarker thresholds. Until now, little attention has been paid to the new ethical challenges that AI brings to the early diagnosis in asymptomatic individuals, beyond contributing to research purposes, when we still lack adequate treatment. The aim of this paper is to explore the ethical arguments put forward (...) for AI aided AD prediction in subjectively asymptomatic individuals and their ethical implications. The ethical assessment is based on a systematic literature search. Thematic analysis was conducted inductively of 18 included publications. The ethical framework includes the principles of autonomy, beneficence, non-maleficence, and justice. Reasons for offering predictive tests to asymptomatic individuals are the right to know, a positive balance of the risk-benefit assessment, and the opportunity for future planning. Reasons against are the lack of disease modifying treatment, the accuracy and explicability of AI aided prediction, the right not to know, and threats to social rights. We conclude that there are serious ethical concerns in offering early diagnosis to asymptomatic individuals and the issues raised by the application of AI add to the already known issues. Nevertheless, pre-symptomatic testing should only be offered on request to avoid inflicted harm. We recommend developing training for physicians in communicating AI aided prediction. (shrink)

As our epistemic ambitions grow, the common and scientific endeavours are becoming increasingly dependent on Machine Learning (ML). The field rests on a single experimental paradigm, which consists of splitting the available data into a training and testing set and using the latter to measure how well the trained ML model generalises to unseen samples. If the model reaches acceptable accuracy, an a posteriori contract comes into effect between humans and the model, supposedly allowing its deployment to target environments. Yet (...) the latter part of the contract depends on human inductive predictions or generalisations, which infer a uniformity between the trained ML model and the targets. The paper asks how we justify the contract between human and machine learning. It is argued that the justification becomes a pressing issue when we use ML to reach ‘elsewheres’ in space and time or deploy ML models in non-benign environments. The paper argues that the only viable version of the contract can be based on optimality (instead of on reliability which cannot be justified without circularity) and aligns this position with Schurz’s optimality justification. It is shown that when dealing with inaccessible/unstable ground-truths (‘elsewheres’ and non-benign targets), the optimality justification undergoes a slight change, which should reflect critically on our epistemic ambitions. Therefore, the study of ML robustness should involve not only heuristics that lead to acceptable accuracies on testing sets. The justification of human inductive predictions or generalisations about the uniformity between ML models and targets should be included as well. Without it, the assumptions about inductive risk minimisation in ML are not addressed in full. (shrink)

A review of Gary Smith and Jay Cordes: The Phantom Pattern Problem: The Mirage of Big Data. New York: Oxford University Press, 2020.

This article investigates religious ideals persistent in the datafication of information society. Its nodal point is Thomas Bayes, after whom Laplace names the primal probability algorithm. It reconsiders their mathematical innovations with Laplace's providential deism and Bayes' singular theological treatise. Conceptions of divine justice one finds among probability theorists play no small part in the algorithmic data-mining and microtargeting of Cambridge Analytica. Theological traces within mathematical computation are emphasized as the vantage over large numbers shifts to weights beyond enumeration in (...) probability theory. Collateral secularizations of predestination and theodicy emerge as probability optimizes into Bayesian prediction and machine learning. The paper revisits the semiotics and theism of Peirce and a given beyond the probable in Whitehead to recontextualize the critiques of providence by Agamben and Foucault. It reconsiders datafication problems alongside Nietzschean valuations. Religiosity likely remains encoded within the very algorithms presumed purified by technoscientific secularity or mathematical dispassion. (shrink)

Scientists depend on complex computational systems that are often ineliminably opaque, to the detriment of our ability to give scientific explanations and detect artifacts. Some philosophers have s...

Lake et al. propose three criteria which, they argue, will bring artificial intelligence (AI) systems closer to human cognitive abilities. In this paper, we explore the application of these criteria to a particular domain of human cognition: our capacity for moral reasoning. In doing so, we explore a set of considerations relevant to the development of AI moral decision-making. Our main focus is on the relation between dual-process accounts of moral reasoning and model-free/model-based forms of machine learning. We also discuss (...) how work in embodied and situated cognition could provide a valu- able perspective on future research. (shrink)

The paper proposes a synthesis between human scientists and artificial representation learning models as a way of augmenting epistemic warrants of realist theories against various anti-realist attempts. Towards this end, the paper fleshes out unconceived alternatives not as a critique of scientific realism but rather a reinforcement, as it rejects the retrospective interpretations of scientific progress, which brought about the problem of alternatives in the first place. By utilising adversarial machine learning, the synthesis explores possibility spaces of available evidence for (...) unconceived alternatives providing modal knowledge of what is possible therein. As a result, the epistemic warrant of synthesised realist theories should emerge bolstered as the underdetermination by available evidence gets reduced. While shifting the realist commitment away from theoretical artefacts towards modalities of the possibility spaces, the synthesis comes out as a kind of perspectival modelling. (shrink)

An important problem with machine learning is that when label number n>2, it is very difficult to construct and optimize a group of learning functions, and we wish that optimized learning functions are still useful when prior distribution P(x) (where x is an instance) is changed. To resolve this problem, the semantic information G theory, Logical Bayesian Inference (LBI), and a group of Channel Matching (CM) algorithms together form a systematic solution. MultilabelMultilabel A semantic channel in the G theory consists (...) of a group of truth functions or membership functions. In comparison with likelihood functions, Bayesian posteriors, and Logistic functions used by popular methods, membership functions can be more conveniently used as learning functions without the above problem. In Logical Bayesian Inference (LBI), every label’s learning is independent. For Multilabel learning, we can directly obtain a group of optimized membership functions from a big enough sample with labels, without preparing different samples for different labels. A group of Channel Matching (CM) algorithms are developed for machine learning. For the Maximum Mutual Information (MMI) classification of three classes with Gaussian distributions on a two-dimensional feature space, 2-3 iterations can make mutual information between three classes and three labels surpass 99% of the MMI for most initial partitions. For mixture models, the Expectation-Maxmization (EM) algorithm is improved and becomes the CM-EM algorithm, which can outperform the EM algorithm when mixture ratios are imbalanced, or local convergence exists. The CM iteration algorithm needs to combine neural networks for MMI classifications on high-dimensional feature spaces. LBI needs further studies for the unification of statistics and logic. (shrink)