Capabilities and Limitations of Feedforward Neural Networks with Multilevel Neurons

This paper proposes a multilevel logic approach to output coding using multilevel neurons in the output layer. Training convergence for a single multilevel perceptron is considered. It has been found that a multilevel neural network classifier with a reduced number of outputs is often able to learn faster and requires fewer weights. Concepts are illustrated with an example of a digit classifier.

• Type: Conference
• Year: 1995
• Where: ISCAS
• Authors: Aleksander Malinowski, Tomasz J. Cholewo, Jacek M. Zurada
• Keywords: Hardware, ISCAS 1995, Multilevel, Multilevel Logic Approach, Single Multilevel Perceptron