A weight initialization method for improving training speed in feedforward neural network

This publication has 16 references indexed in Scilit:

• A stochastically motivated random initialization of pattern classifying MLPs
  Neural Processing Letters, 1996
• Hierarchical neural networks for time-series analysis and control
  Network: Computation in Neural Systems, 1994
• Training feedforward networks with the Marquardt algorithm
  IEEE Transactions on Neural Networks, 1994
• New approach to selection of initial values of weights in neural function approximation
  Electronics Letters, 1993
• Probabilistic Neural Networks
  1993
• Initializing back propagation networks with prototypes
  Neural Networks, 1993
• A learning algorithm for multilayered neural networks based on linear least squares problems
  Neural Networks, 1993
• Statistically controlled activation weight initialization (SCAWI)
  IEEE Transactions on Neural Networks, 1992
• Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights
  1990
• Fast learning in artificial neural systems: multilayer perceptron training using optimal estimation
  1988