NSK, an Object-Oriented Simulator Kernel for Arbitrary Feedforward Neural Networks

An object-oriented neural network simulator kernel is presented. It is based on a general mathematical model for arbitrary feedforward nets. We propose a C++ implementation of this model which satisfies the following requirements : expandability (allowing an easy implementation of a new neural model), portability and efficiency (the kernel does not increase significantly computation times for classic models, compared to a direct object-oriented implementation). Learning algorithms such as gradient-based ones can be written for arbitrary nets and are therefore directly available for every particular model.

• Type: Conference
• Year: 1994
• Where: ICTAI
• Authors: Cédric Gégout, Bernard Girau, Fabrice Rossi
• Keywords: Arbitrary Feedforward Nets, Artificial Intelligence, General Mathematical Model, ICTAI 1994, Object-oriented Neural Network