The theory of neural networks: The Hebb rule and beyond

Haim Sompolinsky

doi:10.1007/bfb0057531

The theory of neural networks: The Hebb rule and beyond

Haim Sompolinsky

Racah Institute of Physics

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

Recent studies of the statistical mechanics of neural network models of associative memory are reviewed. The paper discusses models which have an energy function but depart from the simple Hebb rule. This includes networks with static synaptic noise, dilute networks and synapses that are nonlinear functions of the Hebb rule (e.g., clipped networks). The properties of networks that employ the projection method are reviewed.

Original language	English
Title of host publication	Heidelberg Colloquium on Glassy Dynamics
Subtitle of host publication	Proceedings of a Colloquium on Spin Glasses, Optimization and Neural Networks, Held at the University of Heidelberg, June 9-13, 1986
Publisher	Springer Berlin Heidelberg
Pages	485–527
Volume	275
ISBN (Electronic)	978-3-540-47819-5
ISBN (Print)	978-3-540-17777-7
DOIs	https://doi.org/10.1007/bfb0057531
State	Published - 1 Jan 1987

Access to Document

10.1007/bfb0057531

Cite this

@inbook{4eded06fb24e4807b5f2e232faf01605,

title = "The theory of neural networks: The Hebb rule and beyond",

abstract = "Recent studies of the statistical mechanics of neural network models of associative memory are reviewed. The paper discusses models which have an energy function but depart from the simple Hebb rule. This includes networks with static synaptic noise, dilute networks and synapses that are nonlinear functions of the Hebb rule (e.g., clipped networks). The properties of networks that employ the projection method are reviewed.",

author = "Haim Sompolinsky",

year = "1987",

month = jan,

day = "1",

doi = "10.1007/bfb0057531",

language = "אנגלית",

isbn = "978-3-540-17777-7",

volume = "275",

pages = "485–527",

booktitle = "Heidelberg Colloquium on Glassy Dynamics",

publisher = "Springer Berlin Heidelberg",

}

The theory of neural networks: The Hebb rule and beyond. / Sompolinsky, Haim.
Heidelberg Colloquium on Glassy Dynamics: Proceedings of a Colloquium on Spin Glasses, Optimization and Neural Networks, Held at the University of Heidelberg, June 9-13, 1986. Vol. 275 Springer Berlin Heidelberg, 1987. p. 485–527.

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - The theory of neural networks: The Hebb rule and beyond

AU - Sompolinsky, Haim

PY - 1987/1/1

Y1 - 1987/1/1

N2 - Recent studies of the statistical mechanics of neural network models of associative memory are reviewed. The paper discusses models which have an energy function but depart from the simple Hebb rule. This includes networks with static synaptic noise, dilute networks and synapses that are nonlinear functions of the Hebb rule (e.g., clipped networks). The properties of networks that employ the projection method are reviewed.

AB - Recent studies of the statistical mechanics of neural network models of associative memory are reviewed. The paper discusses models which have an energy function but depart from the simple Hebb rule. This includes networks with static synaptic noise, dilute networks and synapses that are nonlinear functions of the Hebb rule (e.g., clipped networks). The properties of networks that employ the projection method are reviewed.

U2 - 10.1007/bfb0057531

DO - 10.1007/bfb0057531

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.chapter???

SN - 978-3-540-17777-7

VL - 275

SP - 485

EP - 527

BT - Heidelberg Colloquium on Glassy Dynamics

PB - Springer Berlin Heidelberg

ER -

The theory of neural networks: The Hebb rule and beyond

Abstract

Access to Document

Fingerprint

Cite this