Binary perceptron learning algorithm using simplex-method

Authors:
Vladimir Kryzhanovskiy;Irina Zhelavskaya;Jakov Karandashev
Affiliations:
Center of Optical Neural Technologies, Scientific Research Institute for System Analysis, Russian Academy of Sciences, Moscow, Russia;Center of Optical Neural Technologies, Scientific Research Institute for System Analysis, Russian Academy of Sciences, Moscow, Russia;Center of Optical Neural Technologies, Scientific Research Institute for System Analysis, Russian Academy of Sciences, Moscow, Russia
Venue:
ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part I
Year:
2012

Citing 2
Cited 1

Introduction to the theory of neural computation

Introduction to the theory of neural computation
Binary Optimization: On the Probability of a Local Minimum Detection in Random Search

ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing

Vector perceptron learning algorithm using linear programming

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

A number of researchers headed by E. Gardner have proved that a maximum achievable memory load of binary perceptron is 2. A learning algorithm allowing reaching and even exceeding the critical load was proposed. The algorithm was reduced to solving the linear programming problem. The proposed algorithm is sequel to Krauth and Mezard ideas. The algorithm makes it possible to construct networks storage capacity and noise stability of which are comparable to those of Krauth and Mezard algorithm. However suggested modification of the algorithm outperforms.