國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Statistical field theory for neural ...

Dahmen, David.

Statistical field theory for neural networks

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Statistical field theory for neural networksby Moritz Helias, David Dahmen.
作者:	Helias, Moritz.
其他作者:	Dahmen, David.
出版者:	Cham :Springer International Publishing :2020.
面頁冊數:	xvii, 203 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Stochastic differential equations.
電子資源:	https://doi.org/10.1007/978-3-030-46444-8
ISBN:	9783030464448$q(electronic bk.)

Statistical field theory for neural networks
Helias, Moritz.

Statistical field theory for neural networks[electronic resource] /by Moritz Helias, David Dahmen. - Cham :Springer International Publishing :2020. - xvii, 203 p. :ill., digital ;24 cm. - Lecture notes in physics,v.9700075-8450 ;. - Lecture notes in physics ;650..

Introduction -- Probabilities, moments, cumulants -- Gaussian distribution and Wick's theorem -- Perturbation expansion -- Linked cluster theorem -- Functional preliminaries -- Functional formulation of stochastic differential equations -- Ornstein-Uhlenbeck process: The free Gaussian theory -- Perturbation theory for stochastic differential equations -- Dynamic mean-field theory for random networks -- Vertex generating function -- Application: TAP approximation -- Expansion of cumulants into tree diagrams of vertex functions -- Loopwise expansion of the effective action - Tree level -- Loopwise expansion in the MSRDJ formalism -- Nomenclature.

This book presents a self-contained introduction to techniques from field theory applied to stochastic and collective dynamics in neuronal networks. These powerful analytical techniques, which are well established in other fields of physics, are the basis of current developments and offer solutions to pressing open problems in theoretical neuroscience and also machine learning. They enable a systematic and quantitative understanding of the dynamics in recurrent and stochastic neuronal networks. This book is intended for physicists, mathematicians, and computer scientists and it is designed for self-study by researchers who want to enter the field or as the main text for a one semester course at advanced undergraduate or graduate level. The theoretical concepts presented in this book are systematically developed from the very beginning, which only requires basic knowledge of analysis and linear algebra.

ISBN: 9783030464448$q(electronic bk.)

Standard No.: 10.1007/978-3-030-46444-8doiSubjects--Topical Terms:

185784
Stochastic differential equations.

LC Class. No.: QA274.23

Dewey Class. No.: 519.22

Statistical field theory for neural networks
LDR:02602nmm a2200337 a 4500 001 585505
003 DE-He213
005 20200820043533.0
006 m d
007 cr nn 008maaau
008 210311s2020 sz s 0 eng d
020 $a 9783030464448$q(electronic bk.)
020 $a 9783030464431$q(paper)
024 7 $a 10.1007/978-3-030-46444-8 $2 doi
035 $a 978-3-030-46444-8
040 $a GP $c GP
041 0 $a eng
050 4 $a QA274.23
072 7 $a PHS $2 bicssc
072 7 $a SCI040000 $2 bisacsh
072 7 $a PHS $2 thema
082 0 4 $a 519.22 $2 23
090 $a QA274.23 $b .H475 2020
100 1 $a Helias, Moritz. $3 876546
245 1 0 $a Statistical field theory for neural networks $h [electronic resource] / $c by Moritz Helias, David Dahmen.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a xvii, 203 p. : $b ill., digital ; $c 24 cm.
490 1 $a Lecture notes in physics, $x 0075-8450 ; $v v.970
505 0 $a Introduction -- Probabilities, moments, cumulants -- Gaussian distribution and Wick's theorem -- Perturbation expansion -- Linked cluster theorem -- Functional preliminaries -- Functional formulation of stochastic differential equations -- Ornstein-Uhlenbeck process: The free Gaussian theory -- Perturbation theory for stochastic differential equations -- Dynamic mean-field theory for random networks -- Vertex generating function -- Application: TAP approximation -- Expansion of cumulants into tree diagrams of vertex functions -- Loopwise expansion of the effective action - Tree level -- Loopwise expansion in the MSRDJ formalism -- Nomenclature.
520 $a This book presents a self-contained introduction to techniques from field theory applied to stochastic and collective dynamics in neuronal networks. These powerful analytical techniques, which are well established in other fields of physics, are the basis of current developments and offer solutions to pressing open problems in theoretical neuroscience and also machine learning. They enable a systematic and quantitative understanding of the dynamics in recurrent and stochastic neuronal networks. This book is intended for physicists, mathematicians, and computer scientists and it is designed for self-study by researchers who want to enter the field or as the main text for a one semester course at advanced undergraduate or graduate level. The theoretical concepts presented in this book are systematically developed from the very beginning, which only requires basic knowledge of analysis and linear algebra.
650 0 $a Stochastic differential equations. $3 185784
650 0 $a Neural networks (Computer science) $x Mathematics. $3 239337
650 1 4 $a Statistical Physics and Dynamical Systems. $3 760415
650 2 4 $a Neurosciences. $3 211508
650 2 4 $a Machine Learning. $3 833608
650 2 4 $a Mathematical Models of Cognitive Processes and Neural Networks. $3 567118
650 2 4 $a Probability and Statistics in Computer Science. $3 274053
700 1 $a Dahmen, David. $3 876547
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Lecture notes in physics ; $v 650. $3 451204
856 4 0 $u https://doi.org/10.1007/978-3-030-46444-8
950 $a Physics and Astronomy (SpringerNature-11651)