國立高雄大學圖資館 |

Language: English

Back

Space-time computing with temporal n...

Martonosi, Margaret,

Space-time computing with temporal neural networks

Record Type:	Electronic resources : Monograph/item
Title/Author:	Space-time computing with temporal neural networksJames E. Smith.
Author:	Smith, James E.
other author:	Martonosi, Margaret,
Published:	San Rafael, California :Morgan & Claypool Publishers,2017.
Description:	1 online resource (243 p.)
Subject:	Neural networks (Computer science)
Online resource:	click for full text
ISBN:	1627058907

Space-time computing with temporal neural networks
Smith, James E.

Space-time computing with temporal neural networks[electronic resource] /James E. Smith. - 1st ed. - San Rafael, California :Morgan & Claypool Publishers,2017. - 1 online resource (243 p.) - Synthesis Lectures on Computer Architecture ;39.. - Synthesis Lectures on Computer Architecture ;39..

Includes bibliographical references and index.

Space-time computing with temporal neural networks -- Abstract, Keywords -- Contents -- Figure Credits -- Preface -- Acknowledgments -- Part I. Introduction to Space-Time Computing and Temporal Neural Networks -- Chapter 1. Introduction -- Chapter 2. Space-Time Computing -- Chapter 3. Biological Overview -- Part II. Modeling Temporal Neural Networks -- Chapter 4. Connecting TNNs with Biology -- Chapter 5. Neuron Modeling -- Chapter 6. Computing with Excitatory Neurons -- Chapter 7. System Architecture -- Part III. Extended Design Study: Clustering the MNIST Dataset -- Chapter 8. Simulator Implementation -- Chapter 9. Clustering the MNIST Dataset -- Chapter 10. Summary and Conclusions -- References -- Author Biography.

Understanding and implementing the brain's computational paradigm is the one true grand challenge facing computer researchers. Not only are the brain's computational capabilities far beyond those of conventional computers, its energy efficiency is truly remarkable. This book, written from the perspective of a computer designer and targeted at computer researchers, is intended to give both background and lay out a course of action for studying the brain's computational paradigm. It contains a mix of concepts and ideas drawn from computational neuroscience, combined with those of the author. As background, relevant biological features are described in terms of their computational and communication properties. The brain's neocortex is constructed of massively interconnected neurons that compute and communicate via voltage spikes, and a strong argument can be made that precise spike timing is an essential element of the paradigm. Drawing from the biological features, a mathematics-based computational paradigm is constructed. The key feature is spiking neurons that perform communication and processing in space-time, with emphasis on time. In these paradigms, time is used as a freely available resource for both communication and computation. Neuron models are first discussed in general, and one is chosen for detailed development. Using the model, single-neuron computation is first explored. Neuron inputs are encoded as spike patterns, and the neuron is trained to identify input pattern similarities. Individual neurons are building blocks for constructing larger ensembles, referred to as "columns". These columns are trained in an unsupervised manner and operate collectively to perform the basic cognitive function of pattern clustering. Similar input patterns are mapped to a much smaller set of similar output patterns, thereby dividing the input patterns into identifiable clusters. Larger cognitive systems are formed by combining columns into a hierarchical architecture. These higher level architectures are the subject of ongoing study, and progress to date is described in detail in later chapters. Simulation plays a major role in model development, and the simulation infrastructure developed by the author is described.

ISBN: 1627058907Subjects--Topical Terms:

181982
Neural networks (Computer science)

LC Class. No.: QA76.87

Dewey Class. No.: 006.32

Space-time computing with temporal neural networks
LDR:03870nmm a2200277 i 4500 001 559475
006 m o d
007 cr cn|||||||||
008 191226s2017 cau ob 000 0 eng d
020 $a 1627058907
020 $a 1627059482
020 $a 9781627058902
020 $a 9781627059480
035 $a MCPB0006321
040 $a iG Publishing $b eng $e aacr2 $c iG Publishing
041 0 $a eng
050 0 0 $a QA76.87
082 0 4 $a 006.32
100 1 $a Smith, James E. $3 842600
245 1 0 $a Space-time computing with temporal neural networks $h [electronic resource] / $c James E. Smith.
250 $a 1st ed.
260 $a San Rafael, California : $b Morgan & Claypool Publishers, $c 2017.
300 $a 1 online resource (243 p.)
490 1 $a Synthesis Lectures on Computer Architecture ; $v 39.
504 $a Includes bibliographical references and index.
505 0 $a Space-time computing with temporal neural networks -- Abstract, Keywords -- Contents -- Figure Credits -- Preface -- Acknowledgments -- Part I. Introduction to Space-Time Computing and Temporal Neural Networks -- Chapter 1. Introduction -- Chapter 2. Space-Time Computing -- Chapter 3. Biological Overview -- Part II. Modeling Temporal Neural Networks -- Chapter 4. Connecting TNNs with Biology -- Chapter 5. Neuron Modeling -- Chapter 6. Computing with Excitatory Neurons -- Chapter 7. System Architecture -- Part III. Extended Design Study: Clustering the MNIST Dataset -- Chapter 8. Simulator Implementation -- Chapter 9. Clustering the MNIST Dataset -- Chapter 10. Summary and Conclusions -- References -- Author Biography.
520 3 $a Understanding and implementing the brain's computational paradigm is the one true grand challenge facing computer researchers. Not only are the brain's computational capabilities far beyond those of conventional computers, its energy efficiency is truly remarkable. This book, written from the perspective of a computer designer and targeted at computer researchers, is intended to give both background and lay out a course of action for studying the brain's computational paradigm. It contains a mix of concepts and ideas drawn from computational neuroscience, combined with those of the author. As background, relevant biological features are described in terms of their computational and communication properties. The brain's neocortex is constructed of massively interconnected neurons that compute and communicate via voltage spikes, and a strong argument can be made that precise spike timing is an essential element of the paradigm. Drawing from the biological features, a mathematics-based computational paradigm is constructed. The key feature is spiking neurons that perform communication and processing in space-time, with emphasis on time. In these paradigms, time is used as a freely available resource for both communication and computation. Neuron models are first discussed in general, and one is chosen for detailed development. Using the model, single-neuron computation is first explored. Neuron inputs are encoded as spike patterns, and the neuron is trained to identify input pattern similarities. Individual neurons are building blocks for constructing larger ensembles, referred to as "columns". These columns are trained in an unsupervised manner and operate collectively to perform the basic cognitive function of pattern clustering. Similar input patterns are mapped to a much smaller set of similar output patterns, thereby dividing the input patterns into identifiable clusters. Larger cognitive systems are formed by combining columns into a hierarchical architecture. These higher level architectures are the subject of ongoing study, and progress to date is described in detail in later chapters. Simulation plays a major role in model development, and the simulation infrastructure developed by the author is described.
650 0 $a Neural networks (Computer science) $3 181982
650 0 $a Computational neuroscience. $3 190429
650 0 $a Temporal databases. $3 243716
650 0 $a Space and time. $3 176397
700 1 $a Martonosi, Margaret, $e editor. $3 842601
830 0 $a Synthesis Lectures on Computer Architecture ; $v 39. $3 842602
856 4 0 $u http://portal.igpublish.com/iglibrary/search/MCPB0006321.html $z click for full text