|
1. |
Networks that Learn about Phonological Feature Persistence |
|
Connection Science,
Volume 2,
Issue 4,
1990,
Page 265-278
MICHAEL GASSER,
CHAN-DO LEE,
Preview
|
PDF (258KB)
|
|
ISSN:0954-0091
DOI:10.1080/09540099008915674
出版商:Taylor & Francis Group
年代:1990
数据来源: Taylor
|
2. |
Connectionist Language Users |
|
Connection Science,
Volume 2,
Issue 4,
1990,
Page 279-311
ROBERTB. ALLEN,
Preview
|
PDF (556KB)
|
|
摘要:
Neural networks which act as state machines are applied to a variety of natural language tasks. Both generation of sequences and recognition are considered. Among the generation tasks are descriptions and planning. The recognition tasks include question answering, pronoun reference, action identification, and analogy completion. Overall, these studies introduce the use of connectionist state machines as intelligent agents in which the emphasis is on perception of and interaction with their environment through language; thus the agents are termed connectionist language users (CLUES).
ISSN:0954-0091
DOI:10.1080/09540099008915675
出版商:Taylor & Francis Group
年代:1990
数据来源: Taylor
|
3. |
Learning Distributed Representations of Conceptual Knowledge and their Application to Script-based Story Processing |
|
Connection Science,
Volume 2,
Issue 4,
1990,
Page 313-345
GEUNBAE LEE,
MARGOT FLOWERS,
MICHAELG. DYER,
Preview
|
PDF (627KB)
|
|
摘要:
We propose a new method for developing distributed connectionist representations in order to serve as an adequate foundation for constructing and manipulating conceptual knowledge. In our approach, distributed representations of semantic relations (i.e. propositions) are formed by recirculating the hidden layer in two auto-associative recurrent PDP (parallel distributed processing) networks, and our experiments show that the resulting distributed semantic representations (DSRs) have many desirable properties such as automaticity, portability, structure-encoding ability and similarity-based distributed representations. We have constructed a symbolic/connectionist hybrid script-based story processing system DYNASTY (DYNAmic STory understanding sYstem) which incorporates DSR learning and 6 script related processing modules. Each module communicates through a global dictionary, where DSRs are stored, DYNASTY is able to (1) learn similarity-based distributed representations of concepts and events in everyday scriptal experiences, (2) perform script-based causal chain completion inferences according to the acquired sequential knowledge, and (3) perform script role association and retrieval during script application.
ISSN:0954-0091
DOI:10.1080/09540099008915676
出版商:Taylor & Francis Group
年代:1990
数据来源: Taylor
|
4. |
A Single Layer Higher Order Neural Net and its Application to Context Free Grammar Recognition |
|
Connection Science,
Volume 2,
Issue 4,
1990,
Page 347-370
PETERJ. WYARD,
CHARLES NIGHTINGALE,
Preview
|
PDF (436KB)
|
|
摘要:
A single layer higher order dynamic topology neural net called HODYNE is described, targeted at natural language processing problems, HODYNE has an input layer of nodes containing concatenations of words from the input string, and grows nodes during training which are dependent on the training data. The training procedure also has some novel features. Results are presented on the problem of grammaticality determination. The results are encouraging, with almost perfect performance on unseen test sets derived from simple context-free grammars. An important aspect of this work is that the data sets used in training and testing are larger than is common in the research literature.
ISSN:0954-0091
DOI:10.1080/09540099008915677
出版商:Taylor & Francis Group
年代:1990
数据来源: Taylor
|
5. |
On the Epistemological Status of Dog Breath, or Will the Real Qualia Please Stand Up?: A Reply to Sirloin |
|
Connection Science,
Volume 2,
Issue 4,
1990,
Page 371-372
GARRISONW. COTTRELL,
Preview
|
PDF (31KB)
|
|
ISSN:0954-0091
DOI:10.1080/09540099008915678
出版商:Taylor & Francis Group
年代:1990
数据来源: Taylor
|
6. |
Microcognition: Philosophy, Cognitive Science, and Parallel Distributed Processing A. Clark, Cambridge, MA: MIT/Bradford, 1989 ISBN 0-262-03148-5, xiv + 226 pp., λ14.95 |
|
Connection Science,
Volume 2,
Issue 4,
1990,
Page 373-375
DAN LLOYD,
Preview
|
PDF (60KB)
|
|
ISSN:0954-0091
DOI:10.1080/09540099008915679
出版商:Taylor & Francis Group
年代:1990
数据来源: Taylor
|
7. |
The World Yearbook of New Generation Computing Research and Development Igor Aleksander & Ian Benson (Eds) London, Chapman & Hall, 1988 ISBN 0-946536-46-5, ix+822 pp., £80.00 |
|
Connection Science,
Volume 2,
Issue 4,
1990,
Page 376-378
PAUL DAY,
Preview
|
PDF (58KB)
|
|
ISSN:0954-0091
DOI:10.1080/09540099008915680
出版商:Taylor & Francis Group
年代:1990
数据来源: Taylor
|
8. |
Methods in Neuronal Modeling: From Synapses to Networks C. Koch & I. Segev (Eds) Cambridge, MA: MIT/Bradford, 1989 ISBN 0-262-11133-0, xii + 524 pp., £40.50 |
|
Connection Science,
Volume 2,
Issue 4,
1990,
Page 378-379
HELENM. GIGLEY,
Preview
|
PDF (38KB)
|
|
ISSN:0954-0091
DOI:10.1080/09540099008915681
出版商:Taylor & Francis Group
年代:1990
数据来源: Taylor
|
9. |
Publications Received |
|
Connection Science,
Volume 2,
Issue 4,
1990,
Page 381-382
Preview
|
PDF (33KB)
|
|
ISSN:0954-0091
DOI:10.1080/09540099008915682
出版商:Taylor & Francis Group
年代:1990
数据来源: Taylor
|
|