Negative effects of sufficiently small initialweights on back-propagation neural networks.

Yan Liu Jie Yang Long Li Wei Wu

Published in: J. Zhejiang Univ. Sci. C (2012)

Keyphrases

negative effects
sufficiently small
positive effects
confidence intervals
privacy concerns
upper bound
data sets
information systems
data streams
social networks
training data
state space
machine learning
learning environment
peer to peer