A multilayer neural network with pulse position modulation
暂无分享,去创建一个
The problem of the pulse mode neural network is that the synapse weight is bounded between +1 and −1. In order to enhance the weight range, this paper proposes a new weighting method that is a combination of pulse density modulation and pulse position modulation (PPM). The feasibility of the proposed method is verified by experimental MNN with on-chip learning. A modified back-propagation algorithm is used for the on-chip learning. The experimental results show that the proposed MNN architecture has the ability to handle high-resolution classifying problems and good on-chip learning capability. © 2003 Wiley Periodicals, Inc. Syst Comp Jpn, 34(13): 36–46, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10474
[1] Hiroomi Hikawa. Frequency-based multilayer neural network with on-chip learning and enhanced neuron characteristics , 1999, IEEE Trans. Neural Networks.
[2] Raúl Rojas,et al. Hardware for Neural Networks , 1996 .
[3] Mona E. Zaghloul,et al. VLSI implementation of synaptic weighting and summing in pulse coded neural-type cells , 1992, IEEE Trans. Neural Networks.
[4] Michael A. Shanblatt,et al. Random noise effects in pulse-mode digital multilayer neural networks , 1995, IEEE Trans. Neural Networks.