Cognitive Architectures

Sztuczna inteligencja (AI -Artificial intelligence) "zajmuje się konstruowaniem systemów komputerowych zdolnych do wykonywania poszczególnych czynności poznawczych" (Nęcka, Orzechowski, Szymura 2006, s.35). Paul Thagard (1996) określa projektowanie, budowę i eksperymentowanie z obliczeniowymi modelami umysłu jako główną metodę AI. Przedmiotem tej nauki jest zaś proces myślowy, rozumowanie i racjonalność (Russell, Norvig, 1995 s.4).

The term " Cognitive Architectures " indicates both abstract models of cognition, in natural and artificial agents, and the software instantiations of such models which are then employed in the field of Artificial Intelligence (AI). The main role of Cognitive Architectures in AI is that one of enabling the realization of artificial systems able to exhibit intelligent behavior in a general setting through a detailed analogy with the constitutive and developmental functioning and mechanisms underlying human cognition. We provide a brief overview of the status quo and of the potential role that Cognitive Architectures may serve in the fields of Computational Cognitive Science and Artificial Intelligence (AI) research.

Memory is a crucial cognitive ability that supports the mere existence of humans. When they interact with other people or their environment in daily life, they can remember what happened, when it happened and also recall this kind of information at a later point of time. This recalling helps them
to continue interactions with already encountered environment or remember details of a past experience. To evoke similar experiences between a human and a robot, it is evident that these robots should posses artificial memory systems that can mimic human-like memory characteristics. Inspired by the human cognitive ability, memory, this thesis aims to design and develop an artificial memory system that possesses certain properties of human memory. The memory system presented here is based on the theory of information processing in human memory. What remains central in these
artificial memory systems is the representation of the vast amount of information exchanged between the users and the robot. We take advantage of the Semantic Web language, namely, Resource Description Framework (RDF), to represent this information. Our memory system translates this information to basic memory units, which are defined by RDF triples. These triples, from a single interaction session between the user and the robot, are appended to an RDF graph and form a single episode. These episodes are then stored in a triplestore for long-term persistence. We experiment with recalling the stored information based on several usecases. This memory structure provides  homogeneity for storage and retrieval of information
across the entire memory system. Several experiments were carried out on moderate hardware to evaluate the performance of this memory system and this system showed a fair efficiency in runtime. This memory system also has the ability to scale to larger scenarios of longer periods of interactions, which aligns with the purpose of artificial companions: to turn interactions into relationships (Benyon & Mival 2000).

Reinforcement learning (RL) models of decision-making cannot account for human decisions in the absence of prior reward or punishment. We propose a mechanism for choosing among available options based on goal-option association strengths, where association strengths between objects represent previously experienced object proximity. The proposed mechanism, Goal-Proximity Decision-making (GPD), is implemented within the ACT-R cognitive framework. GPD is found to be more efficient than RL in three maze-navigation simulations. GPD advantages over RL seem to grow as task difficulty is increased. An experiment is presented where participants are asked to make choices in the absence of prior reward. GPD captures human performance in this experiment better than RL.

Concepts of "the self" and "self-awareness", and aspects of the experience of types of consciousness, are explored in terms of "cognitive" systems and their interactions. Some roles of the cerebrum, the cerebellum, and their interactions are considered in relation to sentient consciousness, the sense of self, and conscious regulation of behavior. This 'introductory paper' is composed of modified selected extracts from: totalBRAINtotalMIND Vol.1 : An Integrated Brain/Mind Architecture Part 2: A Cognitive Architecture (pp16 -136) Part 3. Total Brain: structure, development, function, and an integrated neurocognitive architecture (pp137-321). tBtM Vol.1 is now available as an e-book from: http://totalbraintotalmind.co.uk/

Blurb (Book Description from the Publisher website):
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.

This book is about building a mind, from a very practical computational perspective. There may be many philosophical debates about what constitutes a mind and whether specific attempts at building a mind have biological or psychological verisimilitude. The position taken here is quite simply that a mind is a process that receives stimuli and produces actions.  This is a very simple definition indeed, and along with that definition, some interesting design patterns, data structures, and algorithms will be explored. 

You can cite this work as follows:

Miller, M. S. P.  2016.  Building Minds with Patterns.
    ISBN-10: 0-692-54140-1  ISBN-13: 978-0-692-54140-1


The book will soon be available for sale.
.

In the last few years user modeling has become an important research area in Human Computer Interaction. A large amount of research has been conducted in this field where different approaches on user modeling are shown. In this paper, we provide an overview of the field of user modeling and describes the different user model namely, GOMS family of models, cognitive architecture, grammar-based model, and application specific models. We have discussed a few examples of user models in each category. This paper also discusses the future challenges of this research area.

Also available for review at https://tinyurl.com/StrangeVisitor.

We recognize myths for what they indicate about the values and beliefs of the cultures who were the authors and audiences of those myths; many of the earliest communicators of myth were telling stories about subjects they counted as people (somewhat) like themselves. Yet, despite our modern sophistication, today’s consumers of narrative still often treat fictions as though they are real, thinking and feeling people.  We are introduced to Superman, for instance, as a fiction, but circumstance often leads consumers to discursively treat that invented hero as a human subject.  Now, though, we verge on a technological future in which just such sympathies might become functionally useful. In our modern science fiction like Star Trek: The Next Generation and Westworld, we have already begun to imagine how we will come to treat our narrative inventions of tomorrow. Strange Visitor: Subjectivity, Simulation, and the Future of the First Superhero begins to ask what our actual responsibilities will become when fictions can be rendered with volition.  In its opening chapters, the text studies how we humanize a figure like Superman in our own perceptions, and how that treatment--along with his continuing narrative development--makes him a prime candidate for an experiment in complex, highly verisimilitudinous simulation.  Superman is a central point of consideration here simply because there is so much of him to consider. He may be the most content-dense fiction ever created, but the innumerable opportunities consumers have had to get to know the character mean that he is also eminently familiar.  Superman has maintained his presence in our media and discourses, across the decades, as consumer populations have continued to grow and our communications structures have commensurately evolved and expanded. Superman is the subject of this study not because he has become so popular, but because he has managed to stay that way at a particularly sharp inflection point in the history of human communications. 

But, the Man of Steel is often generalized as infallible and, therefore, rather dull.  The first part of this work--an expansive psychological assessment--troubles such a presumption, though, by examining the complex mind that has accrued within decades of narrative, across media, and which must be carefully navigated in any exhaustive analysis.  This first section also considers Superman’s relationship with his media consumers: from how we use him to form childhood bonds with one another, to how we respond to his continuing humanization.  For, Superman is powerfully determined by how audiences actually treat any given instance of the figure as Superman.  Today, we find that we can engage with particularly realistic media, encouraging us even more urgently to invest in the verisimilitude and humanity of the characters and places being presented, and doing so often makes a narrative more appealing.  Accordingly, Superman’s relationship with his own media is particularly convenient to an examination of the intersection between fictional narrative, high technology, and identity negotiation.  To understand Superman's potent humanization, the first half of this text presents an assessment of his identity from multiple essential perspectives, including those of his content creators and consumers, as well as the complex judgments of himself and his fictional society as they have been presented in his narratives. Diegetic evidence is considered in historical and psychological capacities in order to assess how Superman’s media has been constructed--practically from the beginning--to encourage consumers to invest themselves in the figure’s humanity and relatability.

In its second part, Strange Visitor moves from relevant questions of identity into a more practical application of those insights to current and emerging technologies.  We already enjoy vastly interactive ways of engaging with our fictions, and we can anticipate continuing advancements in the verisimilitude, interactability, and spontaneity of artificial intelligences.  Accordingly, fewer and fewer holes in the experiential tapestry of narrative will have to be ignored as both storytelling techniques and rendering technologies continue to evolve.  Soon, what we practically treat as a ‘human’ subject may have more to do with that figure’s specific engageability than with its biology or physical consistency.  Given the view of the detailed project proposal that constitutes the second part of this work, spontaneous, humanlike, autonomous simulations culled from fictional worlds could very well become reality within the foreseeable future.  Emerging from our science fiction dreams, several considerable, real-world technological initiatives would see us reconstruct the intellects of great thinkers, such as Gandhi, Curie, or Hawking. But, reconstructing and functionalizing the consciousness of a real person--living or dead--is an ethically dubious proposition from the start.  Instead of an original personality, though--seemingly ‘complete’ at first, but limited in contextual understanding--what if researchers built a simulated subject from the material of a robustly developed fiction?  If the first of our deep, humanlike engagements with such technology will be the most important, Superman seems a fitting choice, given how we have already embraced him on personal and cultural levels.

But, as real technologies advance toward that imagined outcome, we must also ask how the practical, livable terms of fictionality would change. How would our own responsibilities evolve as we produced and engaged with such personalities?  The prototypical solution I propose here--referred to as the Metropolis Simulation System--could be considered one of Andrew M. Butler’s necessary explorations into the role of the simulacrum (“Postmodernism and Science Fiction” 147).  Whatever of these speculations does or does not bear out, it is my hope with this text to show the reader that we must pay substantial attention to our future relationships with our media and computing technologies. Such a situation need not be feared, though, if we approach with the optimistic combination of thoughtfulness and adventurousness that a character like Superman can inspire.

Strange Visitor is intended for any who might have the interest and/or resources to help realize the rendering of a densely-developed fiction as an exemplary representative of humanlike, fully-engageable general artificial intelligence, including the developers of the many technologies referenced.  Portions of the work might also be used as an introduction into the complexities of mediated identity construction, while the critical questions presented could be utilized in advanced media studies courses, or as portions of a forward-thinking philosophy curriculum. Other segments may benefit discussions on popular fictions generally, the ethics of narrative, or psychological and identiary dynamics.

Dice games were a very popular form of entertainment in antiquity. They were not only known to the ancient Greeks and Romans but also to the Germanic peoples from central Europe. A special kind of dice were the so-called long dice. They had long cuboid shapes and were marked with pips only on four longer sides.  This paper will focus on the findings of the Roman period long dice from Poland. As it turns out these artifacts were mostly found in the context of the Przeworsk culture.  It seems that the long dice were usually owned by males with a good social status. It is hard to say what sorts of games were played with these dice. We can only assume that some of the Roman games were known to the Germanic peoples, like e.g. ludus dudecim scriptorum. It is very possible that the long dice also had certain ritual or mantic properties.

Hay una disputa clásica desde la filosofía hasta la psicología actual si la mente funciona como un sistema unitario para realizar los diferentes procesos cognitivos, o si por el contrario, es un conjunto de sistemas especializados para realizar cada uno de los procesos cognitivos. La posición que defiende un sistema unitario recibe el nombre de holísmo y es defendida por los conexionistas, mientras que la posición que defiende sistemas especializados recibe el nombre de modularidad. Este ensayo busca defender la posición modular que sostiene que la mente es un conjunto de sistemas especializados o módulos con especificidad de dominio.

In this paper, we examine the motivations for research on cognitive architectures and review some candidates that have been explored in the literature. After this, we consider the capabilities that a cognitive architecture should support, some properties that it should exhibit related to representation, organization, performance, and learning, and some criteria for evaluating such architectures at the systems level. In closing, we discuss some open issues that should drive future research in this important area.

Predictive approaches to the mind claim that perception, cognition, and action can be understood in terms of a single framework: a hierarchy of Bayesian models employing the computational strategy of predictive coding. Proponents of this view disagree, however, over the extent to which perception is direct on the predictive approach. I argue that we can resolve these disagreements by identifying three distinct notions of perceptual directness: psychological, metaphysical, and epistemological. I propose that perception is plausibly construed as psychologically indirect on the predictive approach, in the sense of being constructivist or inferential. It would be wrong to conclude from this, however, that perception is therefore indirect in a metaphysical or epistemological sense on the predictive approach. In the metaphysical case, claims about the inferential properties of constructivist perceptual mechanisms are consistent with both direct and indirect solutions to the metaphysical problem of perception (e.g. naïve realism, representationalism, sense datum theory).  In the epistemological case, claims about the inferential properties of constructivist perceptual mechanisms are consistent with both direct and indirect approaches to the justification of perceptual belief. In this paper, I demonstrate how proponents of the predictive approach have conflated these distinct notions of perceptual directness and indirectness, and I propose alternative strategies for developing the philosophical consequences of the approach.

The Emergic Cognitive Model (ECM) is a unified computational model of visual filling-in based on the Emergic Network architecture. The Emergic Network was designed to help realize systems undergoing continuous change. In this thesis, eight different filling-in phenomena are demonstrated under a regime of continuous eye movement (and under static eye conditions as well).

ECM indirectly demonstrates the power of unification inherent with Emergic Networks when cognition is decomposed according to finer-grained functions supporting change. These can interact to raise additional emergent behaviours via cognitive re-use, hence the Emergic prefix throughout. Nevertheless, the model is robust and parameter free. Differential re-use occurs in the nature of model interaction with a particular testing paradigm.

ECM has a novel decomposition due to the requirements of handling motion and of supporting unified modelling via finer functional grains. The breadth of phenomenal behaviour covered is largely to lend credence to our novel decomposition.

The Emergic Network architecture is a hybrid between classical connectionism and classical computationalism that facilitates the construction of unified cognitive models. It helps cutting up of functionalism into finer-grains distributed over space (by harnessing massive recurrence) and over time (by harnessing continuous change), yet simplifies by using standard computer code to focus on the interaction of information flows. Thus while the structure of the network looks neurocentric, the dynamics are best understood in flowcentric terms. Surprisingly, dynamic system analysis (as usually understood) is not involved. An Emergic Network is engineered much like straightforward software or hardware systems that deal with continuously varying inputs.  Ultimately, this thesis addresses the problem of reduction and induction over complex systems, and the Emergic Network architecture is merely a tool to assist in this epistemic endeavour.

ECM is strictly a sensory model and apart from perception, yet it is informed by phenomenology. It addresses the attribution problem of how much of a phenomenon is best explained at a sensory level of analysis, rather than at a perceptual one. As the causal information flows are stable under eye movement, we hypothesize that they are the locus of consciousness, howsoever it is ultimately realized.

I argue that semantics is the study of the proprietary database of a centrally inaccessible and informationally encapsulated input–output system. Its role is to encode and decode partial and defeasible evidence of what speakers are saying. Since information about nonlinguistic context is therefore outside the purview of semantic processing, a sentence’s semantic value is not its content but a partial and defeasible constraint on what it can be used to say. I show how to translate this thesis into a detailed compositional-semantic theory based on the influential framework of Heim and Kratzer. This approach situates semantics within an independently motivated account of human cognitive architecture and reveals the semantics–pragmatics interface to be grounded in the underlying interface between modular and central systems.

For robot intelligence and human-robot interaction (HRI), complex decision-making, interpretation , and adaptive planning processes are great challenges. These require recursive task processing and meta-cognitive reasoning mechanism. Naturally, the human brain realizes these cognitive skills by prefrontal cortex which is a part of the neocortex. Previous studies about neurocognitive robotics would not meet these requirements. Thus, it is aimed at developing a brain-inspired robot control architecture that performs spatial-temporal and emotional reasoning. In this study, we present a novel solution that covers a computational model of the prefrontal cortex for humanoid robots. Computational mechanisms are mainly placed on the bio-physical plausible neural structures embodied in different dynamics. The main components of the system are composed of several computational modules including dorsolateral, ventrolateral, anterior, and medial prefrontal regions. Also, it is responsible for organizing the working memory. A reinforcement meta-learning based explainable artificial intelligence (xAI) procedure is applied to the working memory regions of the computational prefrontal cortex model. Experimental evaluation and verification tests are processed by the developed software framework embodied in the humanoid robot platform. The humanoid robots' perceptual states and cognitive processes including emotion, attention, and intention-based reasoning skills can be observed and controlled via the developed software. Several interaction scenarios are implemented to monitor and evaluate the model's performance. INDEX TERMS Artificial intelligence, brain modeling, cognitive robotics, human-robot interaction.

All Cognitive Architectures have their unique ASMs that are necessary to drive decision making, learning and applicability. Though each Action Selection Mechanisms discussed in this paper presents a valid justification for “how and what” is necessary to solve a problem, they do not focus on “why”  the decision was made. The “why” component is what makes a human a truly unique organism as being right or making the best decision is never only the case. This component will be necessary in modeling human cognition and will bring Artificial Intelligence one step closer to truly representing a human and their though-action-categorization processes.

More and more we hear the complaint that the gap between research and instruction is widening and a vital sense of motivation is falling between the cracks. It is our vision that intelligent computing systems will become a partner in the reintegration of discovery and learning within the inquiry process. We will address certain issues that must be faced if computer media are to have the characteristics necessary to support this integration. The development of the computer to date has required a careful attention to the syntax and semantics of the rather limited symbol systems we have induced them to use. A capacity for communicating in multiple modalities with non-uniform communities of symbol users — for sharing in the discovery of a pluralistic universe — will demand a quantum leap in our understanding of the pragmatic dimensions of symbol use. In the future the capacity for inquiry must permeate the living architecture of the computer system. A computer program that begins to embody these ideas will be discussed.

MIT Press, 2016 (TOC and Chapter 1 available for download)

Philosophers have traditionally assumed that the basic units of knowledge and understanding are concepts, beliefs, and argumentative inferences. In Cognitive Pluralism, Steven Horst proposes that another sort of unit—a mental model of a content domain—is the fundamental unit of understanding. He argues that understanding comes not in word-sized concepts, sentence-sized beliefs, or argument-sized reasoning but in the form of idealized models and in domain-sized chunks. He argues further that this idea of “cognitive pluralism”—the claim that we understand the world through many such models of a variety of content domains—sheds light on a number of problems in philosophy.

Horst first presents the “standard view” of cognitive architecture assumed in mainstream epistemology, semantics, truth theory, and theory of reasoning. He then explains the notion of a mental model as an internal surrogate that mirrors features of its target domain, and puts it in the context of ideas in psychology, philosophy of science, artificial intelligence, and theoretical cognitive science. Finally, he argues that the cognitive pluralist view not only helps to explain puzzling disunities of knowledge but also raises doubts about the feasibility of attempts to “unify” the sciences; presents a model-based account of intuitive judgments; and contends that cognitive pluralism favors a reliabilist epistemology and a “molecularist” semantics. Horst suggests that cognitive pluralism allows us to view rival epistemological and semantic theories not as direct competitors but as complementary accounts, each an idealized model of different dimensions of evaluation.

Largely aided by the findings of the so-called ‘mirror neurons’ the attention to motor activity in action observation has exploded over the last two decades. The idea that we internally ‘mirror’ an observed action by covertly reproducing a version of it has lead to a new strand of implicit simulation theories of action understanding. The basic idea of this sort of simulation theory is that perception of others actions automatically activate our own covert action representations, and then that we can use this shared action representation to understand various aspects of the observed action and possibly infer the goal and/or intentions of the observed agent or maybe predict upcoming actions. There is some disagreement among researchers and theorists as to the function of motor ‘simulation’. It is debated whether it serves as the basis for low-level ‘mind-reading’, i.e. ascription of intentions and various mental states to others (Gallese 2003, 2004, 2007. Gallese & Goldman 1998, Goldman in press, Hurley 2005) or whether the function of the simulation is purely related to understanding the action itself (Jeannerod 2006) or maybe related to anticipating upcoming actions (Kilner et al 2004, Csibra 2005, Prinz 2006). 
What seems to be assumed in most of these simulation theories is that the default role of the motor system in social perception is to ‘mirror’ the observed action or that it is only related to the observed action and not my own action motives and plans. It is these basic assumptions of the passivity of motor resonance that I would like to challenge. The question is whether it is misleading to conceptualize motor resonance simply as a mirroring simulation where we covertly ‘echo’ the observed action? Many studies of the functional properties of mirror neurons (MN) and motor facilitation during perception seem to point to a more complex role of the motor system in action perception (di Pellegrino 1992, Gallese et al 1996, Rizzolati & Craighero 2004). This has recently led to some proposals trying to reinterpret the function of motor activity during action perception and in social situations from a simple mirroring process to an anticipatory process (Kilner et al 2004, Csibra 2005, Prinz 2006) – or simply to abandon the idea of simulation altogether (Gallagher 2007). I think these are interesting proposals, but inspired by historic approaches to motor resonance and recent studies I would like to venture a hypothesis of an even more proactive, context and motivation dependent role of motor activity during action perception (Newman-Norlund et al. 2007, Schie et al. In press, Cheng et al. 2007, Keysers & Perrett 2004, 502). Motor resonance during object perception is by many researchers thought of in terms of affordances; i.e. what the object affords the observer to do (Grèzes et al. 2003). My question is why we should not – albeit extra social levels of complexity - see motor resonance during social perception in a similar way, as potential action sketches ‘afforded’ by own present motivational, senori-motor and perceptual situation. My point is not that we never ‘simulate’ or covertly imitate observed actions, but rather that it is questionable why we should think of this as the default process in normal interactive social contexts. Covert imitation might only take place during special cases of action observation where we exactly take on a passive spectator attitude, and that we therefore might need a broader theory of motor resonance that also explains normal active and interactive cases of action perception. Accordingly, I suggest that experimental paradigms with single observers in one-way social situations often carry an ‘imitation bias’, and that we are in dire need of more research of actual interactive social perception. I conclude that theories of motor resonance in social perception as a passive ‘mirroring’ or low-level simulation are faced with serious empirical challenges, and that the motor system might serve a much more proactive role in social cognition than previously thought.

The mental rotation ability is an essential spatial reasoning skill in human cognition and has proven to be an essential predictor of mathematical and STEM skills, critical and computational thinking. Despite its importance, little is known about when and how mental rotation processes are activated in games explicitly targeting spatial reasoning tasks. In particular, the relationship between spatial abilities and Tetris TM has been analysed several times in the literature. However, these analyses have shown contrasting results between the effectiveness of Tetris-based training activities to improve mental rotation skills. In this work, we studied whether, and under what conditions, such ability is used in the Tetris TM game by explicitly modelling mental rotation via an ACT-R based cognitive model controlling a virtual agent. The obtained results show meaningful insights into the activation of mental rotation during game dynamics. The study suggests the necessity to adapt game dynamics in order to force the activation of this process and, therefore, can be of inspiration to design learning activities based on Tetris TM or redesign the game itself to improve its educational effectiveness.

This paper investigates an approach to the use of fractals in architectural design. Two major aspects are discussed. First, the effect of the direction of the line segments on the generated fractal, as well as, the proportions between the generator and the initiator. Secondly, the meanings attached to the lines segments that constitute the fractal are based on some known architectural organization. The goal is to develop a basis for using fractals to suggest architectural forms.

The discovery of so-called ‘mirror neurons’ - found to respond both to own actions and the observation of similar actions performed by others - has been enormously influential in the cognitive sciences and beyond. Given the self-other symmetry these neurons have been hypothesized as underlying a ‘mirror mechanism’ that lets us share representations and thereby ground core social cognitive functions from intention understanding to linguistic abilities and empathy. I argue that mirror neurons are important for very different reasons. Rather than a symmetric ubiquitous or context- independent mechanism, I propose that these neurons are part of broader sensorimotor circuits, which help us navigate and predict the social affordance space that we meet others in. To develop both the critical and positive project I analyze the interpretive choices and the debate surrounding the mirror neuron research and show how the field is marred by highly questionable assumptions about respectively motor and social cognition. The discovery of mirror neurons - and the sensorimotor circuits of which these neurons are a part – actually empirically challenge many of these tacit assumptions. Findings of sensorimotor goal representations at levels of abstraction well beyond actual sensory information and kinetic movements challenge the idea of motor cognition as primarily output production. Additionally, the focus on 3rd person mindreading of hidden mental states is misguiding the field of social cognition. Much ‘mind-reading’ seems rooted in sensorimotor representations and a developmentally primary 2nd person understanding of actions and the mental lives of others, which precisely breaks the assumed dichotomy between mind and behavior. I propose a Social Affordance model where parallel fronto-parietal sensorimotor circuits support representations not just of other people’s actions but of the overall social affordance space. It is a process that monitors concrete goals and teleological possibilities that the environment affords respectively oneself and other present agents. With this model I hypothesize that the complex spectrum of sensorimotor integrations are indeed essential not only to normal action choice calibration but also to social cognitive abilities, as the sensorimotor teleological representations let us relate to others and understand their action choices in a shared pragmatic and intentional context.

Theories of personality traits refer to qualitatively different explanatory mechanisms, limiting prospects for a consensual paradigm. This article presents a trilevel cognitive science analysis that distinguishes multiple, qualitatively different explanations for expressions of personality. Stable individual differences in processes and content associated with traits are distributed within and between levels of explanations. A unitary and coherent account of traits is thus problematic. The Cognitive-Adaptive Theory of Traits (CATT) provides a conceptual framework that interrelates theories at different levels, and identifies trait coherence with individual differences in strategies for managing adaptive goals. It exemplifies a spirit of explanatory pluralism that accepts disunity in personality theory. That is, it is preferable to work with multiple, conceptually rigorous theories at different levels than to aim for a universal paradigm prematurely.

In this paper we present the rationale adopted for the integration of the knowledge level of DUAL-PECCS, a cognitive system for conceptual representation and categorization, with two different cognitive architectures: SOAR and LIDA. In previous works we already showed how the representational and reasoning framework adopted in DUAL-PECCS was integrable with diverse cognitive architectures, i.e. ACT-R and CLARION, making different representational assumptions and adopting diverse knowledge processing mechanisms. The additional integrations presented here suggest that the underlying knowledge representation and reasoning structure adopted in DUAL-PECCS can be used as a unifying framework for the knowledge level of agents endowed with different cognitive architectures. The current version of the system has been experimentally assessed in a task of conceptual categorization where a target concept illustrated by a simple common-sense linguistic description had to be identified by resorting to a mix of categorization strategies. The output has then been compared to human and artificial responses. The novel integration allowed us to extend our previous evaluation.

In this paper, I examine the functions of cognition between monk and environment, focusing on the everyday craft of monasticism at the Burgundian abbey of Cluny. By the eleventh century, Cluny operated at the center of a powerful monastic empire, and its population of monks tirelessly attended to the upkeep and maintenance of the monastery in addition to their primary duties of learning, reading, prayer, and Mass. To study Cluny's everyday cognitive operations, I adopt a dynamic systems-based methodology of analysis composed of extended mind theory, distributed cognition, and cognitive archeology. I apply this dynamic systems-based analysis in the form of three case studies, demonstrating that medieval life at Cluny constituted a computational and cognitive system wherein cognition was distributed spatially between monk and monastery, socially through tradition and culture, and across time through the construction of task settings.

To jest wersja robocza artykuªu. Wersja ostateczna opublikowana w: Modularno±¢ umysªu, Szymon Wróbel (red.), Pozna«-Kalisz: WP-A UAM, 2007, s. 179-206. Cytowa¢ prosz¦ wersj¦ ostateczn¡. Streszczenie W artykule prezentuj¦ koncepcj¦ modularnego umysªu w wersji zaproponowanej przez Fodora oraz zmodykowane uj¦cie moduªu zaprezentowane przez Jackendoa. W szczegól-no±ci interesuj¡ mnie konsekwencje uj¦cia modularno±ci dla charakterystyki zdolno±ci j¦zykowych i konstrukcji modelu kognitywnego tych»e. Model kompetencji i performancji j¦zykowej oparty o modularno±¢ ograniczon¡ struktur¡ Jackendoa stanowi podstaw¦ implementacji z wykorzystaniem architektury systemu SNePS: gramatyk GATN i sieci semantycznych.

While information technologies increasingly permeate our daily life, they result in a new perception of space. This is reflected both in the very definition of space, and in the behavior of people in it. The article discusses the formation of a new type of K-12 educational institutions, which offers a cognitive space for children. After briefly reviewing the history of education and student-teacher relationship, the article demonstrates a cardinal change in this relationship inflicted by the emergence of new technologies and methods and suggests an impact of this change on the architectural design of schools. The design of Skolkovo Innovation Center International School serves as an example.

For effective human-robot interaction, we argue that robots must gain social-cognitive mechanisms that allow them to function naturally and intuitively during social interactions with humans. However, a lack of consensus on social cognitive processes poses a challenge for how to design such mechanisms for artificial cognitive systems. We discuss a recent integrative perspective of social cognition to provide a systematic theoretical underpinning for computational instantiations of these mechanisms. We highlight several commitments of our approach that we refer to as Engineering Human Social Cognition. We then provide a series of recommendations to facilitate the development of the perceptual, motor, and cognitive architecture for this proposed artificial cognitive system in future work. For each recommendation, we highlight their relation to the discussed social-cognitive mechanisms, provide the rationale for these recommendations and potential benefits, and detail examples of associated computational formalisms that could be leveraged to instantiate our recommendations. Overall, the goal of this paper is to outline an interdisciplinary and multi-theoretic approach to facilitate the design of robots that will one day function, and be perceived, as socially interactive and effective teammates.

Much of our everyday, embodied action comes in the form of smooth coping. Smooth coping is skillful action that has become habituated and ingrained, generally placing less stress on cognitive load than considered and deliberative thought and action. When performed with skill and expertise, walking, driving, skiing, musical performances, and short-order cooking are all examples of the phenomenon. Smooth coping is characterized by its rapidity and relative lack of reflection, both being hallmarks of automatization. Deliberative and reflective actions provide the contrast case. In Dreyfus’ classic view, smooth coping is “mindless” absorption into action, being in the flow, and any reflective thought will only interrupt this flow. Building on the pragmatist account of Dewey, others, such as Sutton, Montero, and Gallagher, insist on the intelligent flexibility built into smooth coping, suggesting that it is not equivalent to automatization. We seek to answer two complementary challenges in this article. First, how might we model smooth coping in autonomous agents (natural or artificial) at fine granularity? Second, we use this model of smooth coping to show how we might implement smooth coping in artificial intelligent agents. We develop a conceptual model of smooth coping in LIDA (Learning Intelligent Decision Agent). LIDA is an embodied cognitive architecture implementing the global workspace theory of consciousness, among other psychological theories. LIDA’s implementation of consciousness enables us to account for the phenomenology of smooth coping, something that few cognitive architectures would be able to do. Through the fine granular analysis of LIDA, we argue that smooth coping is a sequence of automatized actions intermittently interspersed with consciously mediated action selection, supplemented by dorsal stream processes. In other words, non-conscious, automatized actions (whether learned or innate) often require occasional bursts of conscious cognition to achieve the skillful and flexible adjustments of smooth coping. In addition, never-conscious dorsal stream information and associated sensorimotor processes provide further online adjustments during smooth coping. To achieve smooth coping in LIDA we introduce a new module to the LIDA cognitive architecture the Automatized Action Selection sub-module. Our complex model of smooth coping borrows notions of “embodied intelligence” from enactivism and augments these by allowing representations and more detailed mechanisms of conscious control. We explore several extended examples of smooth coping, starting from basic activities like walking and scaling up to more complex tasks like driving and short-order cooking.

A Language is a means of communication among humans. It has a structure and is defined by the rules of grammar, which govern the constitution of sentences, clauses and words. Linguistics, the scientific study of language concerns itself with a wide variety of topics such as syntax and semantics. It concerns itself with how the words in a language are combined to form a sentence and how meaning and information are derived from the sentence based on the context. Natural Language processing as a computational discipline has the goal of getting computers to perform tasks, which involve language such as sentiment analysis, parts of speech tagging, machine translation and conversational agents. Classical NLP consisted of the symbolic paradigm, which was based on modelling grammar using theoretical computer science and using rules based on logic. Later on, statistical and probabilistic models became the standard with noisy channel models and Bayesian inference methods being prevalent. In the last two decades, the increase in computing power and the large amounts of data that is available over the internet has led to increased focus on Machine Learning. Machine Learning paradigms like Hidden Markov Models were successful. In the few years, there has been a surge in the use of Deep Learning for various tasks including NLP. Deep Learning is that subfield of Machine Learning, which creates representations of data using artificial neural networks based on computational graphs. In this paper, we will review how deep learning architectures can be used for the task of machine translation and building conversational agents. Keywords: Recurrent neural networks; long short-term memory networks; Language models; encoder decoder architectures; attention mechanism; I. RECURRENT NEURAL NETWORKS Before we move to our NLP tasks, we need to understand Recurrent Neural Networks. It is assumed that the reader is aware of standard neural networks and their training with back-propagation using gradient descent/adam. In a standard neural network, we assume the individual data points to be independent and identically distributed. RNNs deal with sequential data. Input data consists of a sequence of feature vectors. Time here is an independent variable which iterates through the sequence. The corresponding output is also a sequence. Successive feature vectors in the input are temporally related and cannot be assumed to be independent. In a sequence, the output at one time step not only depends on the input at that time step but also on the inputs at previous time steps. We have a feedback mechanism with connections which form cycles. The hidden layer activations at a time step are given as input back to the hidden layer at the next time step. Such cycles in the computational graph enable us to define recurrence relations. This allows us to capture information from the history of the inputs. Let us define the computations. We have an input layer, a hidden layer and an output layer. Let matrix U denote the input to hidden layer weights, W denote the hidden to hidden recurrence relation weights and V denote the hidden to output weights. Let xt denote the input feature vector at time step t, at denote the pre activations of the hidden state vector and st denote the post activations. ot is the output layer pre-activations and y' t is our predicted output. We share the parameters across time steps.

There are many different approaches to building a system that can engage in autonomous mental development. In this paper we present an approach based on what we term self-understanding, by which we mean the explicit representation of and reasoning about what a system does and doesn't know, and how that knowledge changes under action. We present an architecture and a set of representations used in two robot systems that exhibit a limited degree of autonomous mental development, which we term self-extension. The contributions include: representations of gaps and uncertainty for specific kinds of knowledge, and a goal management and planning system for setting and achieving learning goals.

We propose mapping of neuromodulators on computational
processes that could be used as framework for affective computation based on Lovheim “Cube of emotions” [17] , Plutchik “Wheel of emotions” [25], Tomkins “Theory of affects” [13] and combine this theories in the cognitive architecture of “The emotion machine” by Marvin Minsky [21]. In other words we propose a mechanism of affects (emotions) as neuromodulatory influence on computational processes.

In the field of Artificial Intelligence (AI), efforts to achieve human-like behavior have taken very different paths through time. Cognitive Architectures (CAs) differentiate from traditional AI approaches, due to their intention to model cognitive and behavioral processes by understanding the brain’s structure and their functionalities in a natural way. However, the development of distinct CAs has not been easy, mainly because there is no consensus on the theoretical basis, assumptions or even purposes for their creation nor how well they reflect human function. In consequence, there is limited information about the methodological aspects to construct this type of models. To address this issue, some initial statements are established to contextualize about the origins and directions of cognitive architectures and their development, which help to outline perspectives, approaches and objectives of this work, supported by a brief study of methodological strategies and historical aspec...

In this paper we discuss some of the issues concerning the Memory and Content aspects in the recent debate on the identification of a Standard Model of the Mind (Laird, Lebiere, and Rosenbloom, in press). In particular we focus on the rep-resentational models concerning the Declarative Memories of current Cognitive Architectures (CAs). In doing so we outline some of the main problems affecting the current CAs and suggest that the Conceptual Spaces, a representational framework developed by Gärdenfors, is worth-considering to address such problems. Finally we briefly analyze the alternative representational assumptions employed in the three CAs constituting the current baseline for the Standard Model (i.e. SOAR, ACT-R and Sigma). In doing so, we point out the respective differences and discuss their implications in the light of the analyzed problems.