R. J. Gaynier

A method of training multi-layer networks with heaviside characteristics using internal representations

R. J. Gaynier, Tom Downs, 1993, IEEE International Conference on Neural Networks.

On the Properties of Error Functions that Affect the Speed of Backpropagation Learning

R. J. Gaynier, Tom Downs, 1994 .

Sinusoidal and monotonic transfer functions: Implications for VC dimension

R. J. Gaynier, T. Downs, 1995, Neural Networks.

The use of random weights for the training of multilayer networks of neurons with Heaviside characteristics

R. J. Gaynier, T. Downs, 1995 .