
The role of neuron transfer function in artificial neural networks
Author(s) -
Ruimin Wang,
Zhao Hong
Publication year - 2007
Publication title -
wuli xuebao
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.199
H-Index - 47
ISSN - 1000-3290
DOI - 10.7498/aps.56.730
Subject(s) - transfer function , artificial neural network , computer science , transfer (computing) , function (biology) , limit (mathematics) , content addressable memory , field (mathematics) , bidirectional associative memory , artificial intelligence , mathematics , evolutionary biology , biology , mathematical analysis , parallel computing , pure mathematics , electrical engineering , engineering
By analysis of local field distribution of the neurons in stationary state of associative memory neural networks, the role of the analog neuron transfer function in affecting the neural network performance is re-investigated. Different from the research done before, we find that the analog transfer function has no obvious advantages over the hard limit transfer function. Furthermore, analog transfer function sometimes produces a negative impact on certain functions of the network, such as the maximal storage capacity. We show that in pursuing the same performance a proper design rule is more essential than the choice of the transfer function.