Data and models about recognition and recall of words and non words are unified using a real-time network processing theory. Lexical decision and word frequency effect data are analyzed in terms of theoretical concepts that have unified data about development of circular reactions, imitation of novel sounds, the matching of phonetic to articulatory requirements, serial and paired associate verbal learning, free recall, unitization, categorical perception, selective adaptation, auditory contrast, and word superiority effects. The theory, called adaptive resonance theory, arose from an analysis of how a language system self-organizes in real time in response to its complex input environment. Such an approach emphasizes the moment-by-moment dynamical interactions that control language development, learning, and stability. Properties of language performance emerge from an analysis of the system constraints that govern stable language learning. Concepts such as logogens, verification, automatic activation, interactive activation, limited-capacity processing, conscious attention, serial search, processing stages, speed-accuracy trade-off, situational frequency, familiarity, and encoding specificity are revised and developed using this analysis. Concepts such as adaptive resonance, resonant equilibration of short-term memory, bottom-up adaptive filtering, tQp-down adaptiveteml'late matching, competitive masking field, unitized list representation, temporal order information over item representations,

Recently, on-line adaptation of binary classifiers for tracking have been investigated. On-line learning allows for simple classifiers since only the current view of the object from its surrounding background needs to be discriminiated. However, on-line adaption faces one key problem: Each update of the tracker may introduce an error which, finally, can lead to tracking failure (drifting). The contribution of this paper is a novel on-line semi-supervised boosting method which significantly alleviates the drifting problem in tracking applications. This allows to limit the drifting problem while still staying adaptive to appearance changes. The main idea is to formulate the update process in a semisupervised fashion as combined decision of a given prior and an on-line classifier. This comes without any parameter tuning. In the experiments, we demonstrate real-time tracking of our SemiBoost tracker on several challenging test sequences where our tracker outperforms other on-line tracking methods.

Abstract not found

. Three approaches to the study of mind are distinguished: semanticsbased, phenomena-based and design-based. Requirements for the design-based approach are outlined. It is argued that AI as the design-based approach to the study of mind has a long future, and pronouncements regarding its failure are premature, to say the least. 1. Introduction The death of Artificial Intelligence, or more specifically the failure of the computational approach to the study of mind, is often announced, either by converts to some `new' approach, or by people who don't like the idea of a scientific or mechanistic explanation of how the human mind works. Such announcements are naive insofar as they assume that we already know (a) what can and cannot be explained or modelled in computational terms, and (b) what we are trying to explain or replicate. The first assumption ignores the fact that the study of computation is still in its infancy. The second assumption ignores the depth of our ignorance about the...

Massively parallel networks of relatively simple computing elements offer an attractive and versatile framework for exploring a variety of learning structures and processes for intelligent systems. This paper briefly summarizes the popular learning structures and processes used in such networks. It outlines a range of potentially more powerful alternatives for pattern-directed inductive learning in such systems. It motivates and develops a class of new learning algorithms for massively parallel networks of simple computing elements. We call this class of learning processes generative for they offer a set of mechanisms for constructive and adaptive determination of the network architecture - the number of processing elements and the connectivity among them - as a function of experience. Generative learning algorithms attempt to overcome some of the limitations of some approaches to learning in networks that rely on modification of weights on the links within an otherwise fixed network t...

Spatiotemporal connectionist networks (STCN's) comprise an important class of neural models that can deal with patterns distributed both in time and space. In this paper, we widen the application domain of the taxonomy for supervised STCN's recently proposed by Kremer (2001) to the unsupervised case. This is possible through a reinterpretation of the state vector as a vector of latent (hidden) variables, as proposed by Meinicke (2000). The goal of this generalized taxonomy is then to provide a nonlinear generative framework for describing unsupervised spatiotemporal networks, making it easier to compare and contrast their representational and operational characteristics. Computational properties, representational issues and learning are also discussed and a number of references to the relevant source publications are provided. It is argued that the proposed approach is simple and more powerful than the previous attempts, from a descriptive and predictive viewpoint. We also discuss the relation of this taxonomy with automata theory and state space modeling, and suggest directions for further work.

Human episodic memory provides a seemingly unlimited storage for everyday experiences, and a retrieval system that allows us to access the experiences with partial activation of their components. The system is believed to consist of a fast, temporary storage in the hippocampus, and a slow, longterm storage within the neocortex. This paper presents a neural network model of the hippocampal episodic memory inspired by Damasio's idea of Convergence Zones. The model consists of a layer of perceptual feature maps and a binding layer. A perceptual feature pattern is coarse coded in the binding layer, and stored on the weights between layers. A partial activation of the stored features activates the binding pattern, which in turn reactivates the entire stored pattern. For many configurations of the model, a theoretical lower bound for the memory capacity can be derived, and it can be an order of magnitude or higher than the number of all units in the model, and several orders of magnitude higher than the number of binding-layer units. Computational simulations further indicate that the average capacity is an order of magnitude larger than the theoretical lower bound, and making the connectivity between layers sparser causes an even further increase in capacity. Simulations also show that if more descriptive binding patterns are used, the errors tend to be more plausible (patterns are confused with other similar patterns), with a slight cost in capacity. The convergence-zone episodic memory therefore accounts for the immediate storage and associative retrieval capability and large capacity of the hippocampal memory, and shows why the memory encoding areas can be much smaller than the perceptual maps, consist of rather coarse computational units, and be only sparsely connected t...

Many researchers in AI and cognitive science believe that the complexity of a behavioral description reflects the underlying information processing complexity of the mechanism producing the behavior. This paper explores the foundations of this complexity argument. We first distinguish two types of complexity judgements that can be applied to these descriptions and then argue that neither type can be an intrinsic property of the underlying physical system. In short, we demonstrate how changes in the method of observation can radically alter both the number of apparent states and the apparent generative class of a system's behavioral description. From these examples we conclude that the act of observation can suggest frivolous computational explanations of physical phenomena, up to and including cognition. The Observers' Paradox 3 The daily warmth we experience, my father said, is not transmitted by Sun to Earth but is what Earth does in response to Sun. Measurements, he said, measure ...

Supervised learning procedures for neural networks have recently met with considerable success in learning difficult mappings. So far, however, they have been limited by their poor scaling behaviour, particularly for networks with many hidden layers. A promising alternative is to develop unsupervised learning algorithms by defining objective functions that characterize the quality of an internal representation without requiring knowledge of the desired outputs of the system. Our major goal is to build self-organizing network modules which capture important regularities in the environment in a simple form. A layered hierarchy of such modules should be able to learn in a time roughly linear in the number of layers. We propose that a good objective for perceptual learning is to extract higher-order features that exhibit simple coherence across time or space. This can be done by transforming the input representation into an underlying representation in which the mutual information between ...

This book is an outgrowth of discussions that got started in at least three workshops sponsored by the National Science Foundation (NSF):.A workshop on neurocontrol and aerospace applications held in October 1990, under joint sponsorship from McDonnell Douglas and the NSF programs in Dynamic Systems and Control and Neuroengineering.A workshop on intelligent control held in October 1990, under joint sponsorship from NSF and the Electric Power Research Institute, to scope out plans for a major new joint initiative in intelligent control involving a number of NSF programs.A workshop on neural networks in chemical processing, held at NSF in January-February 1991, sponsored by the NSF program in Chemical Reaction Processes The goal of this book is to provide an authoritative source for two kinds of information: (1) fundamental new designs, at the cutting edge of true intelligent control, as well as opportunities for future research to improve on these designs; (2) important real-world applications, including test problems that constitute a challenge to the entire control community. Included in this book are a series of realistic test problems, worked out through lengthy discussions between NASA, NetJroDyne, NSF, McDonnell Douglas, and Honeywell, which are more than just benchmarks for evaluating intelligent control designs. Anyone who contributes to solving these problems may well be playing a crucial role in making possible the future development of hypersonic vehicles and subsequently the