Abstract
In this paper, the implementation of new digital architecture for a multilayer neural network (MNN) with on-chip learning is discussed. The advantage of using the digital approach is that it can use state-of-the-art VLSI and ULSI implementation techniques. One of the major hard-ware problems in implementing a neural network is the activating function of the neurons. The proposed MNN uses a simple function as the neuron's activating function to reduce the circuit size. Moreover, the proposed MNN has an on-chip learning capability. As the learning algorithm, a backpropagation algorithm is modified for effective hard-wave implementation. The proposed MNN is implemented on a field-programmable gate array (FPGA) to evaluate the learning performance and circuit size.
Similar content being viewed by others
References
White BA, Elmasry MI (1992) The digi-neocognitron: a digital neocognitron neural network model for VLSI. IEEE Trans Neural Networks 3:73–85
Lehmann C, Viredaz M, Blayo F (1993) (A generic systolic array building block for neural networks with on-chip learning. IEEE Trans Neural Networks 4(3)
Hikawa H (1997) Learning performance of multilayer neural network with threshold neurons, ITC-CSCC'97, vol. II, pp 1065–1068
Hikawa H (1995) Implementation of simplified multilayer neural networks with on-chip learning. IEEE ICNN'95, vol 4, pp 1633–1637
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Sato, K., Hikawa, H. Implementation of multilayer neural network with threshold neurons and its analysis. Artif Life Robotics 3, 170–175 (1999). https://doi.org/10.1007/BF02481135
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02481135