Connectionist AI Research Articles

Merging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Powered Autonomous Agents

Merging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Powered Autonomous Agents

ANALYSIS OF SYMBOLIC AI AND CONNECTIONIST AI APPROACHES

ANALYSIS OF SYMBOLIC AI AND CONNECTIONIST AI APPROACHES

Food information engineering

AbstractFood information engineering relies on statistical and AI techniques (e.g., symbolic, connectionist, and neurosymbolic AI) for collecting, storing, processing, diffusing, and putting food information in a form exploitable by humans and machines. Food information is collected manually and automatically. Once collected, food information is organized using tabular data representation schema, symbolic, connectionist or neurosymbolic AI techniques. Once collected, processed, and stored, food information is diffused to different stakeholders using appropriate formats. Even if neurosymbolic AI has shown promising results in many domains, we found that this approach is rarely used in the domain of food information engineering. This paper aims to serve as a good reference for food information engineering researchers. Unlike existing reviews on the subject, we cover all the aspects of food information engineering and we linked the paper to online resources built using Open Research Knowledge Graph. These resources are composed of templates, comparison tables of research contributions and smart reviews. All these resources are organized in the “Food Information Engineering” observatory and will be continually updated with new research contributions.

Looking Back, Looking Ahead: Symbolic versus Connectionist AI

The ongoing debate between symbolic and connectionist AI attends to some of the most fundamental issues in the field. In this column, I briefly review the evolution of the unfolding discussion. I also point out that there is a lot more to intelligence than the symbolic and connectionist views of AI.

Looking back, looking ahead: Symbolic versus connectionist AI

AbstractThe ongoing debate between symbolic and connectionist AI attends to some of the most fundamental issues in the field. In this column, I briefly review the evolution of the unfolding discussion. I also point out that there is a lot more to intelligence than the symbolic and connectionist views of AI.

Edge Intelligence for Object Detection in Blockchain-Based Internet of Vehicles: Convergence of Symbolic and Connectionist AI

Reliable detection of objects is a crucial requirement to improve the safety of the visual Internet of Vehicles (V-IoVs). The resemblance of objects to each other or the background makes the detection of objects difficult. The traditional connectionist artificial intelligence (All-based object detection model is a potential approach to increase detection performance, but it has poor interpretability and high computational complexity. Edge intelligence has demonstrated a considerably good balance between efficiency and computation complexity, integrating multi-access edge computing and AI. In this article, an edge AI framework is designed to perform the object detection task, and a novel abductive learning algorithm is proposed to realize the interpretability and robustness of AI in the V-IoV system. Based on the you only look once (YOLO) classifier, the abductive model is used to learn from the data, which combines symbolic and connectionist AI. Moreover, blockchain is developed for model sharing. Compared to the state of the art, simulation results show the high accuracy of the proposed algorithm. Moreover, the proposed approach has interpretability and strong robustness.

Capacitas Ex Machina: Are Computerised Assessmets of Mental Capacity a Benchmark or 'Red Line' for Artificial Intelligence?

This paper traces the history of computers in medicine, focusing on the rise of Expert Systems (ES) in the mid-20th century, to the rise of connectionist AI research in its latter half, and ultimately the development of Automated Mental State Detection (AMSD), fMRI scanning, and human brain interfaces. Following the critique of Joseph Weizenbaum in Computer Power and Human Reason (1976), the paper examines theoretical, practical, and ethical problems for implementing these systems in the real world, and how mental health law and psychiatry are likely to be impacted by near term technological advances which will increasingly 'objectify' the diagnosis and treatment of mental disorders. It concludes with a discussion for how computational reasoning could--and indeed should--operate in the context of mental capacity decisions in England and Wales, and suggests that the use of machines to assess mental capacity should be a Red Line for the ingress of AI and related technologies. It concludes with reflections on the legal implications of this claim, and identifies opportunities for further research.

Selection for Representation in Higher-Order Adaptation

A theory of the evolution of mind cannot be complete without an explanation of how cognition became representational. Artificial approximations of cognitive evolution do not, in general, produce representational cognition. We take this as an indication that there is a gap in our understanding of what drives evolution towards representational solutions, and propose a theory to fill this gap. We suggest selection for learning and selection for second order learning as the causal factors driving the emergence of innate and acquired forms of representation, respectively. Cognition is commonly viewed as a black box--selection works on externally visible behaviour alone, with little regard for implementation structure. Yet even if implementation structure is not constrained by selection on behaviour, implementation structure does affect how easy or difficult it is to make specific modifications to the behaviour. Hence selection for learning can affect the implementation structure of behaviour. Similarly, the implementation structure of learning ability itself is not under direct selection, but selection for second order learning can affect the implementation structure of first order learning. We argue that these indirect selection effects guide evolution towards representational implementations, as structural alignment between implementation structure and environment structure guarantees that simple changes in the environment can be met with simple changes in implementation. We illustrate the theory with examples of computational investigations, and discuss how the theory may help put representational cognition within reach of purely connectionist AI.

Representing, binding, retrieving and unifying relational knowledge using pools of neural binders

Abstract For a long time, connectionist architectures have been criticized for having propositional fixation, lack of compositionality and, in general, for their weakness in representing sophisticated symbolic information and processing it. This work offers a novel approach that allows full integration of symbolic AI with the connectionist paradigm. We show how to encode and process relational knowledge using Artificial Neural Networks (ANNs), such as Boltzmann Machines. The neural architecture uses a working memory (WM), consisting of pools of “binders”, and a long-term synaptic-memory that can store a large relational knowledge-base (KB). A compact variable binding mechanism is proposed which dynamically allocates ensembles of neurons when a query is clamped; retrieving KB items till a solution emerges in the WM. We illustrate the proposal through non-trivial predicate unification problems: knowledge items are only retrieved into the WM upon need, and unified, graph-like structures emerge at equilibrium as an activation pattern of the neural network. Our architecture is based on the fact that some attractor-based ANNs may be viewed as performing constraint satisfaction, where, at equilibrium, fixed-points maximally satisfy a set of weighted constraints. We show how to encode relational graphs as neural activation in WM and how to use constraints that are encoded in synapses, in order to retrieve and process such complex structures. Both procedural (the unification algorithm) and declarative knowledge (logic formulae) are first expressed as constraints and then used to generate (or learn) weighted synaptic connections. The architecture has no central control and is inherently robust to unit failures. Contrary to previous connectionist suggestions, this approach is expressive, compact, accurate, and goal directed. The mechanism is universal and has a simple underlying computational principle. As such, it may be further adapted for applications that combine the advantages of both connectionist and traditional symbolic AI and may be used in modeling aspects of human reasoning.

Computer Modeling and the Fate of Folk Psychology

Although Paul Churchland and Jerry Fodor both subscribe to the so‐called theory‐theory– the theory that folk psychology (FP) is an empirical theory of behavior – they disagree strongly about FP’s fate. Churchland contends that FP is a fundamentally flawed view analogous to folk biology, and he argues that recent advances in computational neuroscience and connectionist AI point toward development of a scientifically respectable replacement theory that will give rise to a new common‐sense psychology. Fodor, however, wagers that FP will be largely preserved and vindicated by scientific investigations of behavior. Recent findings by developmental psychologists, I argue, will push both Churchlandians and Fodorians toward the pessimistic view that FP is a misguided theory that will never be displaced, because it is, so to speak, built into our cognitive systems. I explore the possibility of preserving optimism by rejecting the theory‐theory and adopting the simulation theory, a competing view developed by Robert Gordon, Alvin Goldman, and Jane Heal. According to simulationists, common‐sense interpretation of behavior is accomplished by means of pretense‐like operations that deploy the cognitive system’s own reasoning capabilities in a disengaged manner. Since on this view no theory‐like set of principles would be needed, the simulation theory seems to enjoy a simplicity advantage over the theory‐theory. Steven Stich and Shawn Nichols, however, contend that as the cognitive system would require special mechanisms for disengaged operation, the simplicity question cannot be resolved until suitable computational models are developed. I describe a set of models I have constructed to meet this need, and I discuss the contribution such models can make to determining FP’s fate.

Consciousness: Perspectives from symbolic and connectionist AI

While consciousness has not been a major concern of most AI researchers, some theorists have tried to explore how computational models might explain consciousness. I explore how far computational models might go in explaining consciousness, focusing on three aspects of conscious mental states: their instrinsic intentionality, the awareness a subject has of the contents of these intentional states, and the distinctive qualitative character of these states. I describe and evaluate strategies for developing connectionist systems that satisfy these aspects of consciousness.

A Neurocomputational Perspective: The Nature of Mind and the Structure of Science.

If we are to solve the central problems in the philosophy of science, Paul argues, we must draw heavily on the resources of the emerging sciences of the mind/brain. In Neurocomputational Perspective, Churchland illustrates the fertility of the concepts and data drawn from the study of the brain and from the study of artificial networks that model the brain. These concepts bring an unexpected coherence to scattered issues in the philosophy of science, new solutions to old philosophical problems, and new possibilities of science itself. Neurocomputational Perspective collects the most influential of Churchland's recent essays in the philosophy of mind, and introduces a number of ground breaking new essays in the philosophy of science. The essays in part 1 form a systematic treatment of the major problems in the philosophy of mind, as seen from the perspective of the philosophy of science and also from the perspective of computational neuroscience and connectionist AI. The nature of mental representations, of sensory qualia, of psychological explanation and of human self understanding all receive significant new treatment, and reaffirms his well known position that our folk psychology must eventually be reduced, perhaps to a mature cognitive neurobiology, or else be displaced by some new framework that does cohere with emerging theories of brain function. In part 2, provides a coherent and unified alternative conception, in neurocomputational terms of the many issues central to the philosophy of science. These include the nature of theories, the theory-ladenness of perception, the nature of conceptual unification and theoretical simplicity, thenature of paradigms, the kinematics and dynamics of conceptual change, the nature of abductive inference, and the nature of explanatory understanding. Collectively these present a new conception of science. Paul M. is Professor of Philosophy and member of the Cognitive Science Faculty at the University of California at San Diego. A Bradford Book.

Connectionist AI, symbolic AI, and the brain

Connectionist AI systems are large networks of extremely simple numerical processors, massively interconnected and running in parallel. There has been great progress in the connectionist approach, and while it is still unclear whether the approach will succeed, it is also unclear exactly what the implications for cognitive science would be if it did succeed. In this paper I present a view of the connectionist approach that implies that the level of analysis at which uniform formal principles of cognition can be found is the subsymbolic level, intermediate between the neural and symbolic levels. Notions such as logical inference, sequential firing of production rules, spreading activation between conceptual units, mental categories, and frames or schemata turn out to provide approximate descriptions of the coarse-grained behaviour of connectionist systems. The implication is that symbol-level structures provide only approximate accounts of cognition, useful for description but not necessarily for constructing detailed formal models.