Biological networks are capable of gradual learning based on observing a large number of exemplars over time as well as of rapidly memorizing specific events as a result of a single exposure. The focus of research in neural networks has been on gradual learning, and the modeling of one-shot memorization has received relatively little attention. Nevertheless, the development of biologically plausible computational models of rapid memorization is of considerable value, since such models would enhance our understanding of the neural processes underlying episodic memory formation. A few researchers have attempted the computational modeling of rapid (one-shot) learning within a framework described variably as recruitment learning and vicinal algorithms. Here it is shown that recruitment learning and vicinal algorithms can be grounded in the biological phenomena of long-term potentiation and longterm depression. Toward this end, a computational abstraction of LTP and LTD is presented, and an "algorithm" for the recruitment of binding-detector (or coincidence-detector) cells is described and evaluated using biologically realistic data.

this report. Kautz [79] modeled plan recognition logically in a manner that allowed goals and plans to be described at various levels of abstraction. Etzioni et al. [94, 95, 92, 93] developed a version space algorithm for plan recognition that is provably sound and polynomial time [94, 93]. Weld et al. developed goal recognition algorithms using inductive logic programming [90] and version-space algebra [89, 168, 88] in the context of programming by demonstration

Introduction Research on integrated neural-symbolic systems has made significant progress in the recent past. In particular the understanding of ways to deal with symbolic knowledge within connectionist systems (also called artificial neural networks) has reached a critical mass which enables the community to strive for applicable implementations and use cases. Recent work has covered a great variety of logics used in artificial intelligence and provides a multitude of techniques for dealing with them within the context of artificial neural networks. Already in the pioneering days of computational models of neural cognition, the question was raised how symbolic knowledge can be represented and dealt with within neural networks. The landmark paper [McCulloch and Pitts, 1943] provides fundamental insights how propositional logic can be processed using simple artificial neural networks. Within the following decades, however, the topic did not receive much attention as research in arti

Neural-symbolic systems are hybrid systems that integrate symbolic logic and neural networks. The goal of neural-symbolic integration is to benefit from the combination of features of the symbolic and connectionist paradigms of artificial intelligence. This paper introduces a new neural network architecture based on the idea of fibring logical systems. Fibring allows one to combine di#erent logical systems in a principled way. Fibred neural networks may be composed not only of interconnected neurons but also of other networks, forming a recursive architecture. A fibring function then defines how this recursive architecture must behave by defining how the networks in the ensemble relate to each other, typically by allowing the activation of neurons in one network (A) to influence the change of weights in another network (B). Intuitively, this can be seen as training network B at the same time that one runs network A. We show that, in addition to being universal approximators like standard feedforward networks, fibred neural networks can approximate any polynomial function to any desired degree of accuracy, thus being more expressive than standard feedforward networks.

We readily acquire memories of events and situations in our daily lives. There is a broad consensus that the hippocampal system (HS) plays a critical role in the encoding and retrieval of such "episodic" memories. But how the HS subserves this mnemonic function is not fully understood. This article presents a computational model, SMRITI,that demonstrates how a transient pattern of activity representing an event can be transformed rapidly into a persistent and robust memory trace as a result of long-term potentiation within structures whose architecture and circuitry resemble those of the HS. Predictions and implications of the model are discussed. LONG ABSTRACT We readily remember events and situations in our daily lives and rapidly acquire memories of specific events by watching a telecast or reading a newspaper. There is a broad consensus that the hippocampal system (HS), consisting of the hippocampal formation and neighboring cortical areas, plays a critical role in the encoding and retrieval of such "episodic" memories. But how the HS subserves this mnemonic function is not fully understood. This article presents a computational model, SMRITI, that demonstrates how a cortically expressed transient pattern of activity representing an event can be transformed rapidly into a persistent and robust memory trace as a result of long-term potentiation within structures whose architecture and circuitry resemble those of the HS. Memory traces formed by the model respond to partial cues, and at the same time, reject similar but erroneous cues. During retrieval these memory traces, acting in concert with cortical circuits encoding semantic, causal, and procedural knowledge, can recreate activation-based representations of memorized events. The model explicates the representa...

Graphs of the single-step operator for first-order logic programs --- displayed in the real plane --- exhibit self-similar structures known from topological dynamics, i.e. they appear to be fractals, or more precisely, attractors of iterated function systems. We show that this observation can be made mathematically precise. In particular, we give conditions which ensure that those graphs coincide with attractors of suitably chosen iterated function systems, and conditions which allow the approximation of such graphs by iterated function systems or by fractal interpolation. Since iterated function systems can easily be encoded using recurrent radial basis function networks, we eventually obtain connectionist systems which approximate logic programs in the presence of function symbols.

The performance of symbolic inference tasks has long been a challenge to connectionists. In this paper, we present an extended survey of this area. Existing connectionist inference systems are reviewed, with particular reference to how they perform variable binding and rulebased reasoning and whether they involve distributed or localist representations. The benefits and disadvantages of different representations and systems are outlined, and conclusions drawn regarding the capabilities of connectionist inference systems when compared with symbolic inference systems or when used for cognitive modelling.

Abstract: In my book How the Mind Works, I defended the theory that the human mind is a naturally selected system of organs of computation. Jerry Fodor claims that ‘the mind doesn’t work that way ’ (in a book with that title) because (1) Turing Machines cannot duplicate humans ’ ability to perform abduction (inference to the best explanation); (2) though a massively modular system could succeed at abduction, such a system is implausible on other grounds; and (3) evolution adds nothing to our understanding of the mind. In this review I show that these arguments are flawed. First, my claim that the mind is a computational system is different from the claim Fodor attacks (that the mind has the architecture of a Turing Machine); therefore the practical limitations of Turing Machines are irrelevant. Second, Fodor identifies abduction with the cumulative accomplishments of the scientific community over millennia. This is very different from the accomplishments of human common sense, so the supposed gap between human cognition and computational models may be illusory. Third, my claim about biological specialization, as seen in organ systems, is distinct from Fodor’s own notion of encapsulated modules, so the limitations of the latter are

A connectionist model capable of performing rapid inferences to establish explanatory and referential coherence is described. The model's

We consider recurrent neural networks which deal with symbolic formulas, terms, or, generally speaking, tree-structured data. Approaches like the recursive autoassociative memory, discrete-time recurrent networks, folding networks, tensor construction, holographic reduced representations, and recursive reduced descriptions fall into this category. They share the basic dynamics of how structured data are processed: the approaches recursively encode symbolic data into a connectionistic representation or decode symbolic data from a connectionistic representation by means of a simple neural function. In this paper, we give an overview of the ability of neural networks with these dynamics to encode and decode tree-structured symbolic data. The correlated tasks, approximating and learning mappings where the input domain or the output domain may consist of structured symbolic data, are examined as well.