Open AccessHopfield Neural Networks with Unbounded Monotone Activation Functions
Author(s) -
Nassereddine Tatar
Publication year - 2012
Publication title -
advances in artificial neural systems
Language(s) - English
Resource type - Journals
eISSN - 1687-7608
pISSN - 1687-7594
DOI - 10.1155/2012/571358
Subject(s) - monotone polygon , hopfield network , computer science , artificial neural network , activation function , convergence (economics) , exponential function , mathematical optimization , mathematics , artificial intelligence , mathematical analysis , geometry , economics , economic growth
For the Hopfield Neural Network problem we consider unbounded monotone nondecreasing activation functions. We prove convergence to zero in an exponential manner provided that we start with sufficiently small initial data
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom