Results 11  20
of
51
Computational Complexity Of Neural Networks: A Survey
, 1994
"... . We survey some of the central results in the complexity theory of discrete neural networks, with pointers to the literature. Our main emphasis is on the computational power of various acyclic and cyclic network models, but we also discuss briefly the complexity aspects of synthesizing networks fr ..."
Abstract

Cited by 22 (6 self)
 Add to MetaCart
. We survey some of the central results in the complexity theory of discrete neural networks, with pointers to the literature. Our main emphasis is on the computational power of various acyclic and cyclic network models, but we also discuss briefly the complexity aspects of synthesizing networks from examples of their behavior. CR Classification: F.1.1 [Computation by Abstract Devices]: Models of Computationneural networks, circuits; F.1.3 [Computation by Abstract Devices ]: Complexity Classescomplexity hierarchies Key words: Neural networks, computational complexity, threshold circuits, associative memory 1. Introduction The currently again very active field of computation by "neural" networks has opened up a wealth of fascinating research topics in the computational complexity analysis of the models considered. While much of the general appeal of the field stems not so much from new computational possibilities, but from the possibility of "learning", or synthesizing networks...
Low Entropy Coding with Unsupervised Neural Networks
"... ed on visual and speech data. The ability of the network to automatically generate wavelet codes from natural images is demonstrated. These bear a close resemblance to 2D Gabor functions, which have previously been used to describe physiological receptive fields, and as a means of producing compact ..."
Abstract

Cited by 20 (0 self)
 Add to MetaCart
ed on visual and speech data. The ability of the network to automatically generate wavelet codes from natural images is demonstrated. These bear a close resemblance to 2D Gabor functions, which have previously been used to describe physiological receptive fields, and as a means of producing compact image representations. Keywords: neural networks, unsupervised learning, selforganisation, feature extraction, information theory, redundancy reduction, sparse coding, imaging models, occlusion, image coding, speech coding. Declaration This dissertation is the result of my own original work, except where reference is made to the work of others. No part of it has been submitted for any other university degree or diploma. Its length, including captions, footnotes, appendix and bibliography, is approximately 58000 words. Acknowledgements I would like first and foremost to thank Richard Prager, my supervisor, fo
The Enhanced LBG Algorithm
, 2001
"... Clustering applications cover several elds such as audio and video data compression, pattern recognition, computer vision, medical image recognition, etc. In this paper we present a new clustering algorithm called Enhanced LBG (ELBG). It belongs to the hard and Kmeans vector quantization groups an ..."
Abstract

Cited by 19 (1 self)
 Add to MetaCart
Clustering applications cover several elds such as audio and video data compression, pattern recognition, computer vision, medical image recognition, etc. In this paper we present a new clustering algorithm called Enhanced LBG (ELBG). It belongs to the hard and Kmeans vector quantization groups and derives directly from the simpler LBG. The basic idea we have developed is the concept of utility of a codeword, a powerful instrument to overcome one of the main drawbacks of clustering algorithms: generally, the results achieved are not good in the case of a bad choice of the initial codebook. We will present our experimental results showing that ELBG is able to nd better codebooks than previous clustering techniques and the computational complexity is virtually the same as the simpler LBG.
Neural Networks and Complexity Theory
 In Proc. 17th International Symposium on Mathematical Foundations of Computer Science
, 1992
"... . We survey some of the central results in the complexity theory of discrete neural networks, with pointers to the literature. 1 Introduction The recently revived field of computation by "neural" networks provides the complexity theorist with a wealth of fascinating research topics. While much of ..."
Abstract

Cited by 14 (4 self)
 Add to MetaCart
. We survey some of the central results in the complexity theory of discrete neural networks, with pointers to the literature. 1 Introduction The recently revived field of computation by "neural" networks provides the complexity theorist with a wealth of fascinating research topics. While much of the general appeal of the field stems not so much from new computational possibilities, but from the possibility of "learning", or synthesizing networks directly from examples of their desired inputoutput behavior, it is nevertheless important to pay attention also to the complexity issues: firstly, what kinds of functions are computable by networks of a given type and size, and secondly, what is the complexity of the synthesis problems considered. In fact, inattention to these issues was a significant factor in the demise of the first stage of neural networks research in the late 60's, under the criticism of Minsky and Papert [51]. The intent of this paper is to survey some of the centra...
Rules for the cortical map of ocular dominance and orientation columns
 Neural Networks
, 1994
"... AbstractThree computational rules are sufficient to generate model cortical maps that simulate the interrelated structure of cortical ocular dominance and orientation columns: a noise input. a spatial band passfilter. and competitive normalization across all feature dimensions. The data of Blasdel ..."
Abstract

Cited by 11 (2 self)
 Add to MetaCart
AbstractThree computational rules are sufficient to generate model cortical maps that simulate the interrelated structure of cortical ocular dominance and orientation columns: a noise input. a spatial band passfilter. and competitive normalization across all feature dimensions. The data of Blasdel from optical imaging experiments reveal cortical map fractures, singularities. and linear zones that are fit by the model. In particular. singularities in orientation preference tend to occur in the centers of ocular dominance columns, and orientation contours tend to intersect ocular dominance columns at right angles. The model embodies a universal computational substrate that all models of cortical map development and adult function need to realize in some form.
A SelfOrganizing Map that Learns the Semantic Similarity of Reusable Software Components
, 1994
"... . This paper is concerned with the application of Kohonen's selforganizing map in the area of software reuse. Although software reuse has a long historical tradition in research, what is still missing is an appropriate way to structure software libraries according to the semantic similarities of th ..."
Abstract

Cited by 11 (2 self)
 Add to MetaCart
. This paper is concerned with the application of Kohonen's selforganizing map in the area of software reuse. Although software reuse has a long historical tradition in research, what is still missing is an appropriate way to structure software libraries according to the semantic similarities of the stored software components. In this paper we describe an approach to overcome this inconvenience by applying Kohonen's selforganizing map to the description of software components. As a result we obtain a semantically structured software library which is paramount to conventional approaches. 1. Introduction The area of software reuse is concerned with the development of software systems by using already existing components instead of developing the whole system from scratch. In general, reusable entities during the software development process are the following: objectcode modules, sourcecode modules, specifications, and test data. One can distinguish between components which are devel...
A SelfOrganizing Connectionist Model of Bilingual Processing
"... Current connectionist models of bilingual language processing have been largely restricted to localist stationary models. To fully capture the dynamics of bilingual processing, we present SOMBIP, a selforganizing model of bilingual processing that has learning characteristics. SOMBIP consists of tw ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
Current connectionist models of bilingual language processing have been largely restricted to localist stationary models. To fully capture the dynamics of bilingual processing, we present SOMBIP, a selforganizing model of bilingual processing that has learning characteristics. SOMBIP consists of two interconnected selforganizing neural networks, coupled with a recurrent neural network that computes lexical cooccurrence constraints. Simulations with our model indicate that (1) the model can account for distinct patterns of the bilingual lexicon without the use of language nodes or language tags, (2) it can develop meaningful lexicalsemantic categories through selforganizing processes, and (3) it can account for a variety of priming and interference effects based on associative pathways between phonology and semantics in the lexicon, and (4) it can explain lexical representation in bilinguals with different levels of proficiency and working memory capacity. These capabilities of our model are due to its design characteristics in that (a) it combines localist and distributed properties of processing, (b) it combines representation and learning, and (c) it combines lexicon and sentences in bilingual processing. Thus, SOMBIP serves as a new model of bilingual processing and provides a new perspective on connectionist bilingualism. It has the potential of explaining a wide variety of empirical and theoretical issues in bilingual research.
A theory of interactive parallel processing: new capacity measures and predictions for a response time inequality series
, 2004
"... The authors present a theory of stochastic interactive parallel processing with special emphasis on channel interactions and their relation to system capacity. The approach is based both on linear systems theory augmented with stochastic elements and decisional operators and on a metatheory of paral ..."
Abstract

Cited by 11 (4 self)
 Add to MetaCart
The authors present a theory of stochastic interactive parallel processing with special emphasis on channel interactions and their relation to system capacity. The approach is based both on linear systems theory augmented with stochastic elements and decisional operators and on a metatheory of parallel channels ’ dependencies that incorporates standard independent and coactive parallel models as special cases. The metatheory is applied to OR and AND experimental paradigms, and the authors establish new theorems relating response time performance in these designs to earlier and novel issues. One notable outcome is the remarkable processing efficiency associated with linear parallelchannel systems that include mutually positive interactions. The results may offer insight into perceptual and cognitive configural–holistic processing systems.
Binary Rule Generation via Hamming Clustering
 IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
, 2002
"... The generation of a set of rules underlying a classification problem is performed by applying a new algorithm, called Hamming Clustering (HC). It reconstructs the andor expression associated with any Boolean function from a training set of samples. The basic ..."
Abstract

Cited by 10 (7 self)
 Add to MetaCart
The generation of a set of rules underlying a classification problem is performed by applying a new algorithm, called Hamming Clustering (HC). It reconstructs the andor expression associated with any Boolean function from a training set of samples. The basic
An architecture for BehaviorBased reinforcement learning,” Adaptive Behavior
 Animals, Animats, Software Agents, Robots, Adaptive Systems
, 2005
"... This paper introduces an integration of reinforcement learning and behaviorbased control designed to produce realtime learning in situated agents. The model layers a distributed and asynchronous reinforcement learning algorithm over a learned topological map and standard behavioral substrate to cr ..."
Abstract

Cited by 9 (4 self)
 Add to MetaCart
This paper introduces an integration of reinforcement learning and behaviorbased control designed to produce realtime learning in situated agents. The model layers a distributed and asynchronous reinforcement learning algorithm over a learned topological map and standard behavioral substrate to create a reinforcement learning complex. The topological map creates a small and taskrelevant state space that aims to make learning feasible, while the distributed and asynchronous nature of the model make it compatible with behaviorbased design principles. We present the design, implementation and results of an experiment that requires a mobile robot to perform puck foraging in three artificial arenas using the new model, a random decision making model, and a layered standard reinforcement learning model. The results show that our model is able to learn rapidly on a real robot in a real environment, learning and adapting to change more quickly than both alternative models. We show that the robot is able to make the best choices it can given its drives and experiences using only local decisions and therefore displays planning behavior without the use of classical planning techniques. 1