The notion of intelligence is relevant to several fields of research, including cognitive and comparative psychology, neuroscience, artificial intelligence, and philosophy, among others. However, there is little agreement within and across these fields on how to characterise and explain intelligence. I put forward a behavioural, operational characterisation of intelligence that can play an integrative role in the sciences of intelligence, as well as preserve the distinctive explanatory value of the notion, setting it apart from the related concepts of cognition and (...) rationality. Finally, I examine a popular hypothesis about the underpinnings of intelligence: the capacity to manipulate internal representations of the environment. I argue that the hypothesis needs refinement, and that so refined, it applies only to some forms of intelligence. (shrink)

How are new Bayesian hypotheses generated within the framework of predictive processing? This explanatory framework purports to provide a unified, systematic explanation of cognition by appealing to Bayes rule and hierarchical Bayesian machinery alone. Given that the generation of new hypotheses is fundamental to Bayesian inference, the predictive processing framework faces an important challenge in this regard. By examining several cognitive‐level and neurobiological architecture‐inspired models of hypothesis generation, we argue that there is an essential difference between the two types of (...) models. Cognitive‐level models do not specify how they can be implemented in brains and include structures and assumptions that are external to the predictive processing framework. By contrast, neurobiological architecture‐inspired models, which aim to better resemble brain processes, fail to explain important capacities of cognition, such as categorization and few‐shot learning. The “scaling‐up” challenge for proponents of predictive processing is to explain the relationship between these two types of models using only the theoretical and conceptual machinery of Bayesian inference. (shrink)

Perception solves computationally demanding problems at lightning fast speed. It recovers sophisticated representations of the world from degraded inputs, often in a matter of milliseconds. Any theory of perception must be able to explain how this is possible; in other words, it must be able to explain perception’s computational tractability. One of the few attempts to move toward such an explanation is the information encapsulation hypothesis, which posits that perception can be fast because it keeps computational costs low by forgoing (...) access to information stored in cognition. I argue that we have no compelling reason to believe that encapsulation explains (or even contributes to an explanation of) perceptual tractability, and much reason to doubt it. This is because there exist much deeper computational challenges for perception than information access, and these threaten to make the costs of access irrelevant. If this is right, it undermines a core computational motivation for encapsulation and sends us back to the drawing board for explanations of perceptual tractability. (shrink)

Neither the hype exemplified in some exaggerated claims about deep neural networks (DNNs), nor the gloom expressed by Bowers et al. do DNNs as models in vision science justice: DNNs rapidly evolve, and today's limitations are often tomorrow's successes. In addition, providing explanations as well as prediction and image-computability are model desiderata; one should not be favoured at the expense of the other.

The topic of this dissertation is the nature of linguistic competence, the capacity to understand and produce sentences of natural language. I defend the empiricist account of linguistic competence embedded in the connectionist cognitive science. This strand of cognitive science has been opposed to the traditional symbolic cognitive science, coupled with transformational-generative grammar, which was committed to nativism due to the view that human cognition, including language capacity, should be construed in terms of symbolic representations and hardwired rules. Similarly, linguistic (...) competence in this framework was regarded as being innate, rule-governed, domain-specific, and fundamentally different from performance, i.e., idiosyncrasies and factors governing linguistic behavior. I analyze state-of-the-art connectionist, deep learning models of natural language processing, most notably large language models, to see what they can tell us about linguistic competence. Deep learning is a statistical technique for the classification of patterns through which artificial intelligence researchers train artificial neural networks containing multiple layers that crunch a gargantuan amount of textual and/or visual data. I argue that these models suggest that linguistic competence should be construed as stochastic, pattern-based, and stemming from domain-general mechanisms. Moreover, I distinguish syntactic from semantic competence, and I show for each the ramifications of the endorsement of a connectionist research program as opposed to the traditional symbolic cognitive science and transformational-generative grammar. I provide a unifying front, consisting of usage-based theories, a construction grammar approach, and an embodied approach to cognition to show that the more multimodal and diverse models are in terms of architectural features and training data, the stronger the case is for the connectionist linguistic competence. I also propose to discard the competence vs. performance distinction as theoretically inferior so that a novel and integrative account of linguistic competence originating in connectionism and empiricism that I propose and defend in the dissertation could be put forward in scientific and philosophical literature. (shrink)

Many researchers and intellectuals warn about extreme risks from artificial intelligence. However, these warnings typically came without systematic arguments in support. This paper provides an argument that AI will lead to the permanent disempowerment of humanity, e.g. human extinction, by 2100. It rests on four substantive premises which it motivates and defends: first, the speed of advances in AI capability, as well as the capability level current systems have already reached, suggest that it is practically possible to build AI systems (...) capable of disempowering humanity by 2100. Second, due to incentives and coordination problems, if it is possible to build such AI, it will be built. Third, since it appears to be a hard technical problem to build AI which is aligned with the goals of its designers, and many actors might build powerful AI, misaligned powerful AI will be built. Fourth, because disempowering humanity is useful for a large range of misaligned goals, such AI will try to disempower humanity. If AI is capable of disempowering humanity and tries to disempower humanity by 2100, then humanity will be disempowered by 2100. This conclusion has immense moral and prudential significance. (shrink)

A basic deep neural network (DNN) is trained to exhibit a large set of input–output dispositions. While being a good model of the way humans perform some tasks automatically, without deliberative reasoning, more is needed to approach human‐like artificial intelligence. Analysing recent additions brings to light a distinction between two fundamentally different styles of computation: content‐specific and non‐content‐specific computation (as first defined here). For example, deep episodic RL networks draw on both. So does human conceptual reasoning. Combining the two takes (...) advantage of the complementary costs and benefits of each. It also offers a better model of human cognitive competence. (shrink)

The feature-matching approach pioneered by Amos Tversky remains a groundwork for psychological models of similarity and categorization but is rarely explicitly justified considering recent advances in thinking about cognition. While psychologists often view similarity as an unproblematic foundational concept that explains generalization and conceptual thought, long-standing philosophical problems challenging this assumption suggest that similarity derives from processes of higher-level cognition, including inference and conceptual thought. This paper addresses three specific challenges to Tversky’s approach: (i) the feature-selection problem, (ii) the problem (...) of cognitive implausibility, and (iii) the problem of unprincipled tweaking. It subsequently supports key insights from Tversky’s account based on recent developments in Bayesian modeling of cognition. A novel computational view of similarity as inference is proposed that addresses each challenge by considering the contrast class as constitutive of similarity and selecting for highly informative features. In so doing, this view illustrates the ongoing promise of the feature-matching approach in explaining perception, generalization and conceptual thought by grounding them in principles of probabilistic inference. (shrink)

In the 1940s, Gilbert Ryle argued that knowing how to do something is not just a matter of being well-regulated but also a matter of self-regulation. Ryle appears to have thought that know-how requires self-regulation in both a backward-looking and forward-looking sense, but both ideas run counter to ordinary intuitions about know-how. The basic idea behind self-regulation, undertaking trials and adjusting to feedback, is captured by the “law of effect.” Daniel Dennett has argued that the “law of effect will not (...) go away”. After updating Dennett’s “Tower of Generate-and-Test” through a broad survey of the empirical literature on learning, I identify a Rylean intuition about intelligence and argue that self-regulation in a forward-looking sense is necessary for know-how. (shrink)

Since the early days of artificial intelligence (AI), many logics have been explored as tools for knowledge representation and reasoning. In the spirit of the Crossley Festscrift and recognizing John Crossley’s diverse interests and his legacy in both mathematical logic and computer science, I discuss examples from my own research that sit in the overlap of logic and AI, with a focus on supporting human–AI interactions.

There is a widely held view that visual representations (images) do not depict negation, for example, as expressed by the sentence, “the train is not coming.” The present study focuses on the real-world visual representations of photographs and comic (manga) illustrations and empirically challenges the question of whether humans and machines, that is, modern deep neural networks, can recognize visual representations as expressing negation. By collecting data on the captions humans gave to images and analyzing the occurrences of negation phrases, (...) we show some evidence that humans recognize certain images as expressing negation. Furthermore, based on this finding, we examined whether or not humans and machines can classify novel images as expressing negation. The humans were able to correctly classify images to some extent, as expected from the analysis of the image captions. On the other hand, the machine learning model of image processing was only able to perform this classification at about the chance level, not at the same level of performance as the human. Based on these results, we discuss what makes humans capable of recognizing negation in visual representations, highlighting the role of the background commonsense knowledge that humans can exploit. Comparing human and machine learning performances suggests new ways to understand human cognitive abilities and to build artificial intelligence systems with more human-like abilities to understand logical concepts. (shrink)

We review publications in automated scientific discovery using deep learning, with the aim of shedding light on problems with strong connections to philosophy of science, of physics in particular. We show that core issues of philosophy of science, related, notably, to the nature of scientific theories; the nature of unification; and of causation loom large in scientific deep learning. Therefore, advances in deep learning could, and ideally should, have impact on philosophy of science, and vice versa. We suggest lines of (...) further research, and highlight the role ‘theory-based’ AI could have in future developments of the field. (shrink)

Practical ability manifested through robust and reliable task performance, as well as information relevance and well-structured representation, are key factors indicative of understanding in the philosophical literature. We explore these factors in the context of deep learning, identifying prominent patterns in how the results of these algorithms represent information. While the estimation applications of modern neural networks do not qualify as the mental activity of persons, we argue that coupling analyses from philosophical accounts with the empirical and theoretical basis for (...) identifying these factors in deep learning representations provides a framework for discussing and critically evaluating potential machine understanding given the continually improving task performance enabled by such algorithms. (shrink)

L’humilité est usuellement considérée comme une vertu morale, mais aussi épistémique. Une exception à cet égard dans la tradition philosophique est le Commentaire au Premier Alcibiade de Proclus. Celui-ci nous décrit le choix d’Alcibiade par Socrate, les premières étapes de leur relation pédagogique, mais aussi et surtout les principes théoriques qui les justifient, en faisant la part belle à ce qu’on pourrait appeler l’orgueil épistémique, pourvu de trois composantes : la fierté (φρόνημα), le mépris (καταφρονεῖν, etc.) et l’ambition (φιλοτιμία). Après (...) une étude terminologique des notions pertinentes pour l’argument de Proclus à ce sujet, cet article tente de le reconstituer par une analyse des trois composantes décrites par Proclus et de leurs relations, en se concentrant sur l’aspect particulièrement développé dans les pages du Commentaire préservées : l’orgueil comme marque du potentiel de l’élève. Il décrit ensuite comment cette reconnaissance s’inscrit dans la dynamique plus générale de purification de l’orgueil d’Alcibiade par la méthode socratique, et revient enfin à la question philosophique initiale de la valeur éducative de l’humilité et de l’orgueil épistémiques. (shrink)

Mental representations remain the central posits of psychology after many decades of scrutiny. However, there is no consensus about the representational format(s) of biological cognition. This paper provides a survey of evidence from computational cognitive psychology, perceptual psychology, developmental psychology, comparative psychology, and social psychology, and concludes that one type of format that routinely crops up is the language-of-thought (LoT). We outline six core properties of LoTs: (i) discrete constituents; (ii) role-filler independence; (iii) predicate–argument structure; (iv) logical operators; (v) inferential (...) promiscuity; and (vi) abstract content. These properties cluster together throughout cognitive science. Bayesian computational modeling, compositional features of object perception, complex infant and animal reasoning, and automatic, intuitive cognition in adults all implicate LoT-like structures. Instead of regarding LoT as a relic of the previous century, researchers in cognitive science and philosophy-of-mind must take seriously the explanatory breadth of LoT-based architectures. We grant that the mind may harbor many formats and architectures, including iconic and associative structures as well as deep-neural-network-like architectures. However, as computational/representational approaches to the mind continue to advance, classical compositional symbolic structures – that is, LoTs – only prove more flexible and well-supported over time. (shrink)

Real causal systems are complicated. Despite this, causal learning research has traditionally emphasized how causal relations can be induced on the basis of idealized events, i.e. those that have been mapped to binary variables and abstracted from time. For example, participants may be asked to assess the efficacy of a headache-relief pill on the basis of multiple patients who take the pill (or not) and find their headache relieved (or not). In contrast, the current study examines learning via interactions with (...) continuous dynamic systems, systems that include continuous variables that interact over time (and that can be continuously observed in real time by the learner). To explore such systems, we develop a new framework that represents a causal system as a network of stationary Gauss--Markov (``\OU'') processes and show how such \textit{OU networks} can express complex dynamic phenomena such as feedback loops and oscillations. To assess adult's abilities to learn such systems, we conducted an experiment in which participants were asked to identify the causal relationships of a number of OU networks, potentially carrying out multiple, temporally-extended interventions. We compared their judgments to a normative model for learning OU networks as well as a range of alternative and heuristic learning models from the literature. We found that, although participants exhibited substantial learning of such systems, they committed certain systematic errors. These successes and failures were best accounted for by a model that describes people as focusing on pairs of variables, rather than evaluating the evidence with respect to the full space of possible structural models. We argue that our approach provides both a principled framework for exploring the space of dynamic learning environments as well as new algorithmic insights into how people interact successfully with a continuous causal world. (shrink)

We seem to learn and use concepts in a variety of heterogenous “formats”, including exemplars, prototypes, and theories. Different strategies have been proposed to account for this diversity. Hybridists consider instances in different formats to be instances of a single concept. Pluralists think that each instance in a different format is a different concept. Eliminativists deny that the different instances in different formats pertain to a scientifically fruitful kind and recommend eliminating the notion of a “concept” entirely. In recent years, (...) hybridism has received the most attention and support. However, we are still lacking a cognitive-computational model for concept representation and processing that would underpin hybridism. The aim of this paper is to advance the understanding of concepts by grounding hybridism in a neuroscientific model within the Predictive Processing framework. In the suggested view, the different formats are not distinct parts of a concept but arise from different ways of processing a functionally unified representational structure. (shrink)

Conviction Narrative Theory (CNT) is a theory of choice underradical uncertainty– situations where outcomes cannot be enumerated and probabilities cannot be assigned. Whereas most theories of choice assume that people rely on (potentially biased) probabilistic judgments, such theories cannot account for adaptive decision-making when probabilities cannot be assigned. CNT proposes that people usenarratives– structured representations of causal, temporal, analogical, and valence relationships – rather than probabilities, as the currency of thought that unifies our sense-making and decision-making faculties. According to CNT, (...) narratives arise from the interplay between individual cognition and the social environment, with reasoners adopting a narrative that feels “right” to explain the available data; using that narrative to imagine plausible futures; and affectively evaluating those imagined futures to make a choice. Evidence from many areas of the cognitive, behavioral, and social sciences supports this basic model, including lab experiments, interview studies, and econometric analyses. We identify 12 propositions to explain how the mental representations (narratives) interact with four inter-related processes (explanation, simulation, affective evaluation, and communication), examining the theoretical and empirical basis for each. We conclude by discussing how CNT can provide a common vocabulary for researchers studying everyday choices across areas of the decision sciences. (shrink)

Despite the success of artificial intelligence, we are still far away from AI that model the world as humans do. This study focuses for explaining human behavior from intuitive mental models’ perspectives. We describe how behavior arises in biological systems and how the better understanding of this biological system can lead to advances in the development of human-like AI. Human can build intuitive models from physical, social, and cultural situations. In addition, we follow Bayesian inference to combine intuitive models and (...) new information to make decisions. We should build similar intuitive models and Bayesian algorithms for the new AI. We suggest that the probability calculation in Bayesian sense is sensitive to semantic properties of the objects’ combination formed by observation and prior experience. We call this brain process as computational meaningfulness and it is closer to the Bayesian ideal, when the occurrence of probabilities of these objects are believable. How does the human brain form models of the world and apply these models in its behavior? We outline the answers from three perspectives. First, intuitive models support an individual to use information meaningful ways in a current context. Second, neuroeconomics proposes that the valuation network in the brain has essential role in human decision making. It combines psychological, economical, and neuroscientific approaches to reveal the biological mechanisms by which decisions are made. Then, the brain is an over-parameterized modeling organ and produces optimal behavior in a complex word. Finally, a progress in data analysis techniques in AI has allowed us to decipher how the human brain valuates different options in complex situations. By combining big datasets with machine learning models, it is possible to gain insight from complex neural data beyond what was possible before. We describe these solutions by reviewing the current research from this perspective. In this study, we outline the basic aspects for human-like AI and we discuss on how science can benefit from AI. The better we understand human’s brain mechanisms, the better we can apply this understanding for building new AI. Both development of AI and understanding of human behavior go hand in hand. (shrink)

Artificial Intelligence is making rapid and remarkable progress in the development of more sophisticated and powerful systems. However, the acknowledgement of several problems with modern machine learning approaches has prompted a shift in AI benchmarking away from task-oriented testing towards ability-oriented testing, in which AI systems are tested on their capacity to solve certain kinds of novel problems. The Animal-AI Environment is one such benchmark which aims to apply the ability-oriented testing used in comparative psychology to AI systems. Here, we (...) present the first direct human-AI comparison in the Animal-AI Environment, using children aged 6–10. We found that children of all ages were significantly better than a sample of 30 AIs across most of the tests we examined, as well as performing significantly better than the two top-scoring AIs, “ironbar” and “Trrrrr,” from the Animal-AI Olympics Competition 2019. While children and AIs performed similarly on basic navigational tasks, AIs performed significantly worse in more complex cognitive tests, including detour tasks, spatial elimination tasks, and object permanence tasks, indicating that AIs lack several cognitive abilities that children aged 6–10 possess. Both children and AIs performed poorly on tool-use tasks, suggesting that these tests are challenging for both biological and non-biological machines. (shrink)

Generalization does not come from repeatedly observing phenomena in numerous settings, but from theories explaining what is general in those phenomena. Expecting future behavior to look like past observations is especially problematic in psychology, where behaviors change when people's knowledge changes. Psychology should thus focus on theories of people's capacity to create and apply new representations of their environments.

In this paper, we explore interaction history as a particular source of pressure for achieving emergent compositional communication in multi-agent systems. We propose a training regime implementing template transfer, the idea of carrying over learned biases across contexts. In the presented method, a sender-receiver dyad is first trained with a disentangled pair of objectives, and then the receiver is transferred to train a new sender with a standard objective. Unlike other methods, the template transfer approach does not require imposing inductive (...) biases on the architecture of the agents. We experimentally show the emergence of compositional communication using topographical similarity, zero-shot generalization and context-independence as evaluation metrics. The presented approach is connected to an important line of work in semiotics and developmental psycholinguistics: it supports a conjecture that compositional communication is scaffolded on simpler communication protocols. (shrink)

A theoretical pillars of vision science in the information-processing tradition is that perception involves unconscious inference. The classic support for this claim is that, since retinal inputs underdetermine their distal causes, visual perception must be the conclusion of a process that starts with premises representing both the sensory input and previous knowledge about the visible world. Focus on this “argument from underdetermination” gives the impression that, if it fails, there is little reason to think that visual processing involves unconscious inference. (...) Here an alternative means of support for this pillar is proposed, based on another foundational challenge for the visual system: recognizing invariant properties of objects in the environment even though anything we encounter is never seen exactly the same way twice. Explaining how the visual system solves this invariance problem requires positing visual processes that exhibit many commonalities with inductive inference. Thus, this novel “argument from invariance” reveals one way in which visual processing clearly involves unconscious inference. (shrink)

Fodor argued that learning a concept by hypothesis testing would involve an impossible circularity. I show that Fodor's argument implicitly relies on the assumption that actually φ-ing entails an ability to φ. But this assumption is false in cases of φ-ing by luck, and just such luck is involved in testing hypotheses with the kinds of generative random sampling methods that many cognitive scientists take our minds to use. Concepts thus can be learned by hypothesis testing without circularity, and it (...) is plausible that this is how humans in fact acquire at least some of their concepts. (shrink)

Despite their popularity, relatively scant attention has been paid to the upshot of Bayesian and predictive processing models of cognition for views of overall cognitive architecture. Many of these models are hierarchical ; they posit generative models at multiple distinct "levels," whose job is to predict the consequences of sensory input at lower levels. I articulate one possible position that could be implied by these models, namely, that there is a continuous hierarchy of perception, cognition, and action control comprising levels (...) of generative models. I argue that this view is not entailed by a general Bayesian/predictive processing outlook. Bayesian approaches are compatible with distinct formats of mental representation. Focusing on Bayesian approaches to motor control, I argue that the junctures between different types of mental representation are places where the transitivity of hierarchical prediction may be broken, and I consider the upshot of this conclusion for broader discussions of cognitive architecture. (shrink)

This paper traces the empiricist program from early debates between nativism and behaviorism within philosophy, through debates about early connectionist approaches within the cognitive sciences, and up to their recent iterations within the domain of deep learning. We demonstrate how current debates on the nature of cognition via deep network architecture echo some of the core issues from the Chomsky/Quine debate and investigate the strength of support offered by these various lines of research to the empiricist standpoint. Referencing literature from (...) both computer science and philosophy, we conclude that the current state of deep learning does not offer strong encouragement to the empiricist side despite some arguments to the contrary. (shrink)

Recent work in the cognitive sciences has argued that beliefs sometimes acquire signaling functions in virtue of their ability to reveal information that manipulates “mindreaders.” This paper sketches some of the evolutionary and design considerations that could take agents from solipsistic goal pursuit to beliefs that serve as social signals. Such beliefs will be governed by norms besides just the traditional norms of epistemology. As agents become better at detecting the agency of others, either through evolutionary history or individual learning, (...) the candidate pool for signaling expands. This logic holds for natural and artificial agents that find themselves in recurring social situations that reward the sharing of one’s thoughts. (shrink)

Collaboration requires agents to coordinate their behavior on the fly, sometimes cooperating to solve a single task together and other times dividing it up into sub‐tasks to work on in parallel. Underlying the human ability to collaborate is theory‐of‐mind (ToM), the ability to infer the hidden mental states that drive others to act. Here, we develop Bayesian Delegation, a decentralized multi‐agent learning mechanism with these abilities. Bayesian Delegation enables agents to rapidly infer the hidden intentions of others by inverse planning. (...) We test Bayesian Delegation in a suite of multi‐agent Markov decision processes inspired by cooking problems. On these tasks, agents with Bayesian Delegation coordinate both their high‐level plans (e.g., what sub‐task they should work on) and their low‐level actions (e.g., avoiding getting in each other's way). When matched with partners that act using the same algorithm, Bayesian Delegation outperforms alternatives. Bayesian Delegation is also a capable ad hoc collaborator and successfully coordinates with other agent types even in the absence of prior experience. Finally, in a behavioral experiment, we show that Bayesian Delegation makes inferences similar to human observers about the intent of others. Together, these results argue for the centrality of ToM for successful decentralized multi‐agent collaboration. (shrink)

Cognitive scientists often describe the mind as constructing and using models of aspects of the environment, but it is not obvious what makes something a model as opposed to a mere representation....

In March 2016, DeepMind's computer programme AlphaGo surprised the world by defeating the world‐champion Go player, Lee Sedol. AlphaGo exhibits a novel, surprising and valuable style of play and has been recognised as “creative” by the artificial intelligence (AI) and Go communities. This article examines whether AlphaGo engages in creative problem solving according to the standards of comparative psychology. I argue that AlphaGo displays one important aspect of creative problem solving (namely mental scenario building in the form of Monte Carlo (...) tree search), while lacking another (domain generality). This analysis has consequences for how we think about creativity in humans and AI. (shrink)

This paper attempts to answer a central question in unsupervised learning: what does it mean to “make sense” of a sensory sequence? In our formalization, making sense involves constructing a symbolic causal theory that both explains the sensory sequence and also satisfies a set of unity conditions. The unity conditions insist that the constituents of the causal theory – objects, properties, and laws – must be integrated into a coherent whole. On our account, making sense of sensory input is a (...) type of program synthesis, but it is unsupervised program synthesis. Our second contribution is a computer implementation, the Apperception Engine, that was designed to satisfy the above requirements. Our system is able to produce interpretable human-readable causal theories from very small amounts of data, because of the strong inductive bias provided by the unity conditions. A causal theory produced by our system is able to predict future sensor readings, as well as retrodict earlier readings, and impute (fill in the blanks of) missing sensory readings, in any combination. In fact, it is able to do all three tasks simultaneously. We tested the engine in a diverse variety of domains, including cellular automata, rhythms and simple nursery tunes, multi-modal binding problems, occlusion tasks, and sequence induction intelligence tests. In each domain, we test our engine's ability to predict future sensor values, retrodict earlier sensor values, and impute missing sensory data. The Apperception Engine performs well in all these domains, significantly out-performing neural net baselines. We note in particular that in the sequence induction intelligence tests, our system achieved human-level performance. This is notable because our system is not a bespoke system designed specifically to solve intelligence tests, but a general-purpose system that was designed to make sense of any sensory sequence. (shrink)

Flexibility is one of the hallmarks of human problem‐solving. In everyday life, people adapt to changes in common tasks with little to no additional training. Much of the existing work on flexibility in human problem‐solving has focused on how people adapt to tasks in new domains by drawing on solutions from previously learned domains. In real‐world tasks, however, humans must generalize across a wide range of within‐domain variation. In this work we argue that representational abstraction plays an important role in (...) such within‐domain generalization. We then explore the nature of this representational abstraction in realistically complex tasks like video games by demonstrating how the same model‐based planning framework produces distinct generalization behaviors under different classes of task representation. Finally, we compare the behavior of agents with these task representations to humans in a series of novel grid‐based video game tasks. Our results provide evidence for the claim that within‐domain flexibility in humans derives from task representations composed of propositional rules written in terms of objects and relational categories. (shrink)

Book Description (Blurb): Cognitive Design for Artificial Minds explains the crucial role that human cognition research plays in the design and realization of artificial intelligence systems, illustrating the steps necessary for the design of artificial models of cognition. It bridges the gap between the theoretical, experimental and technological issues addressed in the context of AI of cognitive inspiration and computational cognitive science. -/- Beginning with an overview of the historical, methodological and technical issues in the field of Cognitively-Inspired Artificial Intelligence, (...) Lieto illustrates how the cognitive design approach has an important role to play in the development of intelligent AI technologies and plausible computational models of cognition. Introducing a unique perspective that draws upon Cybernetics and early AI principles, Lieto emphasizes the need for an equivalence between cognitive processes and implemented AI procedures, in order to realise biologically and cognitively inspired artificial minds. He also introduces the Minimal Cognitive Grid, a pragmatic method to rank the different degrees of biologically and cognitive accuracy of artificial systems in order project and predict their explanatory power with respect to the natural systems taken as source of inspiration. -/- Providing a comprehensive overview of cognitive design principles in constructing artificial minds, this text will be essential reading for students and researchers of artificial intelligence and cognitive science. (shrink)

As modern deep networks become more complex, and get closer to human‐like capabilities in certain domains, the question arises as to how the representations and decision rules they learn compare to the ones in humans. In this work, we study representations of sentences in one such artificial system for natural language processing. We first present a diagnostic test dataset to examine the degree of abstract composable structure represented. Analyzing performance on these diagnostic tests indicates a lack of systematicity in representations (...) and decision rules, and reveals a set of heuristic strategies. We then investigate the effect of training distribution on learning these heuristic strategies, and we study changes in these representations with various augmentations to the training set. Our results reveal parallels to the analogous representations in people. We find that these systems can learn abstract rules and generalize them to new contexts under certain circumstances—similar to human zero‐shot reasoning. However, we also note some shortcomings in this generalization behavior—similar to human judgment errors like belief bias. Studying these parallels suggests new ways to understand psychological phenomena in humans as well as informs best strategies for building artificial intelligence with human‐like language understanding. (shrink)

Butz, Achimova, Bilkey, and Knott provide a topic overview and discuss whether the special issue contributions may imply that event‐predictive abilities constitute a root for conceptual human thought, because they enable complex, mutually beneficial, but also intricately competitive, social interactions and language communication.

RÉSUMÉNous proposons une théorie compatibiliste du libre arbitre, dans la tradition de la philosophie naturalisée, qui tente : 1) de fournir une synthèse de théories bien connues, capable de résoudre certains problèmes de ces dernières; 2) de tenir compte du fait que le libre arbitre a des degrés; 3) d’établir des liens avec la neurobiologie. Nous arguons que le libre arbitre d'un agent varie par degrés en fonction de la capacité de l'agent à faire des hypothèses et à utiliser des (...) théories. Notre modèle met en évidence que des actions «libres» sont consciemment surveillées par l'agent, à travers des croyances, des hypothèses et finalement des théories — d'où l'expression «modèle CMT» (pour Conscious-through-Monitoring-through-Theories). (shrink)

In ‘Computing Machinery and Intelligence’, Turing, sceptical of the question ‘Can machines think?’, quickly replaces it with an experimentally verifiable test: the imitation game. I suggest that for such a move to be successful the test needs to be relevant, expansive, solvable by exemplars, unpredictable, and lead to actionable research. The Imitation Game is only partially successful in this regard and its reliance on language, whilst insightful for partially solving the problem, has put AI progress on the wrong foot, prescribing (...) a top-down approach for building thinking machines. I argue that to fix shortcomings with modern AI systems a nonverbal operationalisation is required. This is provided by the recent Animal-AI Testbed, which translates animal cognition tests for AI and provides a bottom-up research pathway for building thinking machines that create predictive models of their environment from sensory input. (shrink)

This paper is about guessing: how people respond to a question when they aren’t certain of the answer. Guesses show surprising and systematic patterns that the most obvious theories don’t explain. We argue that these patterns reveal that people aim to optimize a tradeoff between accuracy and informativity when forming their guess. After spelling out our theory, we use it to argue that guessing plays a central role in our cognitive lives. In particular, our account of guessing yields new theories (...) of belief, assertion, and the conjunction fallacy—the psychological finding that people sometimes rank a conjunction as more probable than one of its conjuncts. More generally, we suggest that guessing helps explain how boundedly rational agents like us navigate a complex, uncertain world. (shrink)

In recent years, the family of algorithms collected under the term ``deep learning'' has revolutionized artificial intelligence, enabling machines to reach human-like performances in many complex cognitive tasks. Although deep learning models are grounded in the connectionist paradigm, their recent advances were basically developed with engineering goals in mind. Despite of their applied focus, deep learning models eventually seem fruitful for cognitive purposes. This can be thought as a kind of biological exaptation, where a physiological structure becomes applicable for a (...) function different from that for which it was selected. In this paper, it will be argued that it is time for cognitive science to seriously come to terms with deep learning, and we try to spell out the reasons why this is the case. First, the path of the evolution of deep learning from the connectionist project is traced, demonstrating the remarkable continuity, and the differences as well. Then, it will be considered how deep learning models can be useful for many cognitive topics, especially those where it has achieved performance comparable to humans, from perception to language. It will be maintained that deep learning poses questions that cognitive sciences should try to answer. One of such questions is the reasons why deep convolutional models that are disembodied, inactive, unaware of context, and static, are by far the closest to the patterns of activation in the brain visual system. (shrink)

Cognitive science began as a multidisciplinary endeavor to understand how the mind works. Since the beginning, cognitive scientists have been asking questions about the right methodologies and levels of explanation to pursue this goal, and make cognitive science a coherent science of the mind. Key questions include: Is there a privileged level of explanation in cognitive science? How do different levels of explanation fit together, or relate to one another? How should explanations at one level inform or constrain explanations at (...) some other level? Can the different approaches to the mind, brain, and culture be unified? The aim of this issue of topiCS is to provide a platform for discussing different answers to such questions and to facilitate a better understanding between the different strands of thinking about the right levels of explanation in cognitive science. (shrink)

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)

How much would you pay to play a lottery with an “infinite expected payoff?” In the case of the century old, St. Petersburg Paradox, the answer is that the vast majority of people would only pay a small amount. The authors seek to understand this paradox by providing an explanation consistent with a broad, process‐level model of human decision‐making under risk.

This paper analyzes the rapid and unexpected rise of deep learning within Artificial Intelligence and its applications. It tackles the possible reasons for this remarkable success, providing candidate paths towards a satisfactory explanation of why it works so well, at least in some domains. A historical account is given for the ups and downs, which have characterized neural networks research and its evolution from “shallow” to “deep” learning architectures. A precise account of “success” is given, in order to sieve out (...) aspects pertaining to marketing or sociology of research, and the remaining aspects seem to certify a genuine value of deep learning, calling for explanation. The alleged two main propelling factors for deep learning, namely computing hardware performance and neuroscience findings, are scrutinized, and evaluated as relevant but insufficient for a comprehensive explanation. We review various attempts that have been made to provide mathematical foundations able to justify the efficiency of deep learning, and we deem this is the most promising road to follow, even if the current achievements are too scattered and relevant for very limited classes of deep neural models. The authors’ take is that most of what can explain the very nature of why deep learning works at all and even very well across so many domains of application is still to be understood and further research, which addresses the theoretical foundation of artificial learning, is still very much needed. (shrink)