This study of the workings of neural networks in perception and understanding of situations and simple sentences shows that, and how, distributed conceptual constituents are bound together in episodes within an interactive/dynamic architecture of sensorial and pre-motor maps, and maps of conceptual indicators (semantic memory) and individuating indicators (historical, episodic memory). Activation circuits between these maps make sensorial and pre-motor fields in the brain function as episodic maps creating representations, which are expressions in consciousness. It is argued that all consciousness is episodic, consisting of situational or linguistic representations, and that the mind is the whole of all conscious manifestations of the brain. Thought occurs only in the form of linguistic or image representations. The book also discusses the role of consciousness in the relationship between causal and denotational semantics, and its role for the possibility of representations and rules. Four recent controversies in consciousness research are discussed and decided along this model of consciousness: • Is consciousness an internal or external monitoring device of brain states? • Do all conscious states involve thought and judgement? • Are there different kinds of consciousness? • Do we have a one-on-one correspondence between certain brain states and conscious states. The book discusses also the role of consciousness in the relationship between causal and denotational semantics, and its role for the possibility of representations and rules. (Series A)

Presenting research on the computational abilities of connectionist, neural, and neurally inspired systems, this series emphasizes the question of how connectionist or neural network models can be made to perform rapid, short-term types of computation useful in higher cognitive processes. The most recent volumes are directed mainly at researchers in connectionism, analogy, metaphor, and case-based reasoning, but are also suitable for graduate courses in those areas.

Connectionist Models of Learning, Development and Evolution comprises a selection of papers presented at the Sixth Neural Computation and Psychology Workshop - the only international workshop devoted to connectionist models of psychological phenomena. With a main theme of neural network modelling in the areas of evolution, learning, and development, the papers are organized into six sections: The neural basis of cognition Development and category learning Implicit learning Social cognition Evolution Semantics Covering artificial intelligence, mathematics, psychology, neurobiology, and philosophy, it will be an invaluable reference work for researchers and students working on connectionist modelling in computer science and psychology, or in any area related to cognitive science.

Part of a series on cognitive behaviour and science, based on a 1990 conference sponsored by the Cognitive Science Program and the Linguistics Department of Simon Fraser University, Vancouver, British Columbia, Canada.

Connectionist modelling and applications have become a major feature of debate in cognitive psychology. In this book, leading connectionists shed light on current approaches to memory and language modelling.

Covers recent research in connectionism on a range of topics from biology to hardware, and from psychology to philosophy. Topics include: the mind-body problem, neural networks and computing, cognition and non-linear dynamics, language learning and neurobiology.