A class of instantaneously trained neural networks

This paper presents FC networks that are instantaneously trained neural networks that allow rapid learning of non-binary data. These networks, which generalize the earlier CC networks, have been compared against Backpropagation (BP) and Radial Basis Function (RBF) networks and are seen to have excellent performance for prediction of time-series and pattern recognition. The networks can generalize using soft or hard decisions.

• Type: Journal
• Year: 2002
• Where: ISCI
• Authors: Subhash C. Kak
• Keywords: Earlier Cc Networks, FC Networks, ISCI 2002, Neural Networks