摘要:

An approach to develop new game-playing strategies based on artificial evolution of neural networks is presented. Evolution was directed to discover strategies in Othello against a random-moving opponent and later against an alpha - beta search program. The networks discovered first a standard positional strategy, and subsequently a mobility strategy, an advanced strategy rarely seen outside of tournaments. The latter discovery demonstrates how evolutionary neural networks can develop novel solutions by turning an initial disadvantage into an advantage in a changed environment.

ISSN:0954-0091    

DOI:10.1080/09540099509696191

出版商:Taylor & Francis Group    

年代:1995

数据来源: Taylor

摘要:

We describe an alternate approach to visual recognition of handwritten words, wherein an image is converted into a spatio-temporal signal by scanning it in one or more directions, and processed by a suitable connectionist network. The scheme offers several attractive features including shift-invariance, explication of local spatial geometry along the scan direction, a significant reduction in the number of free parameters, the ability to process arbitrarily long images along the scan direction, and a natural framework for dealing with the segmentation/recognition dilemma. Other salient features of the work include the use of a modular and structured approach for network construction and the integration of connectionist components with a procedural component to exploit the complementary strengths of both techniques. The system consists of two connectionist components and a procedural controller. One network concurrently makes recognition and segmentation hypotheses, and another performs refined recognition of segmented characters. The interaction between the networks is governed by the procedural controller. The system is tested on three tasks: isolated digit recognition, recognition of overlapping pairs of digits and recognition of ZIP codes.

ISSN:0954-0091    

DOI:10.1080/09540099509696192

出版商:Taylor & Francis Group    

年代:1995

数据来源: Taylor

摘要:

An implementation of non-regular symbol manipulation with neural networks is presented. In particular, it is shown how a context-free language can be produced with neural networks. The rules of the language are stored as patterns in an attractor neural network. Another such network is used as a working memory, which can be enlarged without changing the production system itself. As a result, the competence of symbol manipulation with neural networks equals that of classical non-regular production systems. In actual behaviour (performance), however, there are differences between the systems, which shows the importance of implementation in the generation of rule-like behaviour.

ISSN:0954-0091    

DOI:10.1080/09540099509696193

出版商:Taylor & Francis Group    

年代:1995

数据来源: Taylor

摘要:

This paper presents an approach to design of a neural architecture for both associative (content-addressed) and address-based memories. Several interesting properties of the memory module are mathematically analyzed in detail. When used as an associative memory, the proposed neural memory module supports recall from partial input patterns, (sequential) multiple recalls and fault-tolerance. When used as an address-based memory, the memory module can provide working space for dynamic representations for symbol processing and shared message-passing among neural network modules within an integrated neural network system. It also provides for real-time update of memory contents by one-shot learning without interference with other stored patterns.

ISSN:0954-0091    

DOI:10.1080/09540099509696194

出版商:Taylor & Francis Group    

年代:1995

数据来源: Taylor

摘要:

A number of recent simulation studies have shown that when feedforward neural nets are trained, using backpropagation, to memorize sets of items in sequential blocks and without negative exemplars, severe retroactive interference or catastrophic forgetting results. Both formal analysis and simulation studies are employed here to show why and under what circumstances such retroactive interference arises. The conclusion is that, on the one hand, approximations to 'ideal' network geometries can entirely alleviate interference if the training data sets have been generated from a learnable function (not arbitrary pattern associations). All that is required is either a representative training set or enough sequential memory sets. However, this elimination of interference comes with cost of a breakdown in discrimination between input patterns that have been learned and those that have not: catastrophic remembering. On the other hand, localized geometries for subfunctions eliminate the discrimination problem but are easily disrupted by new training sets and thus cause catastrophic interference. The paper concludes with a formally guaranteed solution to the problems of interference and discrimination. This is the Hebbian Autoassociative Recognition Memory (HARM) model which is essentially a neural net implementation of a simple look-up table. Although it requires considerable memory resources, when used as a yardstick with which to evaluate other proposed solutions, it uses the same or less resources.

ISSN:0954-0091    

DOI:10.1080/09540099550039264

出版商:Taylor & Francis Group    

年代:1995

数据来源: Taylor

摘要:

Non-isolated randomly interconnected neural nets with chemical markers are investigated, which receive steady or slowly varying excitatory or inhibitory inputs. We extend here our previous studies to include nets of Poisson and Gaussian connectivities. Our results show that the multi-hysteresis loops obtained by applying the steady-state condition for the Gaussian approximation are wider than the corresponding ones of the Poisson case, and they have been slightly shifted to larger values of the parameter sigma + (which is the fraction of external active fibres). Also, in the Gaussian nets, the stable steady states are lower than the corresponding ones of the Poisson nets, whereas the unstable states are higher.

ISSN:0954-0091    

DOI:10.1080/09540099509696196

出版商:Taylor & Francis Group    

年代:1995

数据来源: Taylor

ISSN:0954-0091    

DOI:10.1080/09540099509696197

出版商:Taylor & Francis Group    

年代:1995

数据来源: Taylor

ISSN:0954-0091    

DOI:10.1080/09540099509696198

出版商:Taylor & Francis Group    

年代:1995

数据来源: Taylor