In this report we discuss the use of two simple classifiers to initialise the input-to-hidden layer of a one-hidden-layer neural network. These classifiers divide the input space in convex regions that can be represented by membership functions. These functions are then used to determine the weights of the first layer of a feedforward network.

, , ,
hdl.handle.net/1765/1436
Erasmus School of Economics

Bioch, C., Carsouw, R., & Potharst, R. (1995). On the use of simple classifiers for the initialisation of one-hidden-layer neural nets. Retrieved from http://hdl.handle.net/1765/1436