Handbook of Brain Theory and Neural Networks

Handbook of Brain Theory and Neural Networks

Language: English

Pages: 1136

ISBN: 0262011484

Format: PDF / Kindle (mobi) / ePub


Choice Outstanding Academic Title, 1996.

In hundreds of articles by experts from around the world, and in overviews and "road maps" prepared by the editor, The Handbook of Brain Theory and Neural Networks charts the immense progress made in recent years in many specific areas related to two great questions: How does the brain work? and How can we build intelligent machines?

While many books have appeared on limited aspects of one subfield or another of brain theory and neural networks, the Handbook covers the entire sweep of topics—from detailed models of single neurons, analyses of a wide variety of biological neural networks, and connectionist studies of psychology and language, to mathematical analyses of a variety of abstract neural networks, and technological applications of adaptive, artificial neural networks.

The excitement, and the frustration, of these topics is that they span such a broad range of disciplines including mathematics, statistical physics and chemistry, neurology and neurobiology, and computer science and electrical engineering as well as cognitive psychology, artificial intelligence, and philosophy. Thus, much effort has gone into making the Handbook accessible to readers with varied backgrounds while still providing a clear view of much of the recent, specialized research in specific topics.

The heart of the book, part III, comprises of 267 original articles by leaders in the various fields, arranged alphabetically by title. Parts I and II, written by the editor, are designed to help readers orient themselves to this vast range of material. Part I, Background, introduces several basic neural models, explains how the present study of brain theory and neural networks integrates brain theory, artificial intelligence, and cognitive psychology, and provides a tutorial on the concepts essential for understanding neural networks as dynamic, adaptive systems. Part II, Road Maps, provides entry into the many articles of part III through an introductory "Meta-Map" and twenty-three road maps, each of which tours all the Part III articles on the chosen theme.

 

 

 

 

 

 

 

 

 

 

 

 

coupling to fully integrated neural networks, Neural Computing Surveys, 2:62–93. Plate, T. A., 1995, Holographic reduced representations, IEEE Transactions on Neural Networks, 6:623–641. Rachkovskij, D. A., and Kussul, E. M., 2001, Binding and normalization of binary sparse distributed representations by context-dependent thinning, Neural Computation, 13:411–452. van der Velde, F., 1995, Symbol manipulation with neural networks: Production of a context-free language using a modifiable working

composed of large numbers of local networks (a “network of networks”) suggest that networks like TODAM might be realizable with neural networks. 121 Discussion and Open Questions An often proclaimed virtue of neural networks is their ability to generalize effectively and to do computation based on similarity. Having learned example associations from a training set, the network can then generate correct answers to new examples. Many have pointed out the formal similarity of neural networks to

owners. Most probably, people will use BCI in combination with other sensory interaction modalities (e.g., speech, gestures) and physiological signals (e.g., electromyogram, skin conductivity). Such a multimodal interface will yield a higher bit rate of communication with better reliability than would occur if only brainwaves were utilized. On the other hand, the incorporation of other interaction modalities highlights a critical issue in BCI, namely the importance of filtering out from the

associated to mental tasks, IEEE Trans. on Neural Networks, 11:678–686. Nicolelis, M. A. L., 2001, Actions from thoughts, Nature, 409:403–407. ࡗ Obermaier, B., Mu¨ller, G., and Pfurtscheller, G., 2001, “Virtual Keyboard” controlled by spontaneous EEG activity, in Proceedings of the Inter- 181 national Conference on Artificial Neural Networks, Heidelberg: Springer-Verlag. Roberts, S. J., and Penny, W. D., 2000, Real-time brain-computer interfacing: A preliminary study using Bayesian learning,

in the EEG (see also “Hippocampal Rhythm Generation”). In general, the same brain sources account for the EEG and the MEG, with the reservation that the MEG reflects magnetic fields perpendicular to the skull that are caused by tangential current dipolar fields, whereas the EEG/MEG reflects both radial and tangential fields. This property can be used advantageously to disentangle radial sources lying in the convexity of cortical gyri from tangential sources lying in the sulci. EVENT-RELATED

Download sample

Download