Weight Partitioning for Dynamic Fixed-Point Neuromorphic Computing Systems
- 25 October 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 38 (11) , 2167-2171
Abstract
Neuromorphic computing systems consist of neurons and synapses with limited programmability, and neural networks are modified to be mapped for such a system. In order to map a perceptron with a large number of connections into a hardware neuron with a fixed, small number of synapses, it is decomposed into a tree of perceptrons, which substantially affects the neuron usage and predictive performance. In this paper, we propose two decomposition algorithms that take advantage of plastic connections and the dynamic scaling capability of neurons. One algorithm based on sorting considers the neuron usage first, and the other algorithm based on packing considers the predictive performance first. Our experimental results on two popular deep convolutional neural networks showed that the sorting-based algorithm substantially improved the accuracy at no cost of neurons compared to a previous work, and the packing-based algorithm improved it even further at a small cost of neurons.Keywords
Funding Information
- National Research Foundation of Korea
- Ministry of Education (NRF-2017R1D1A1B03029103)
- Institute for Information and Communications Technology Promotion
- National Research Foundation of Korea (1711073912)
This publication has 7 references indexed in Scilit:
- Group Scissor2017
- Synthesis of activation-parallel convolution structures for neuromorphic architectures2017
- Dot-product engine for neuromorphic computing2016
- Simplifying deep neural networks for neuromorphic architectures2016
- A million spiking-neuron integrated circuit with a scalable communication network and interfaceScience, 2014
- Field Programmable Neural Array for feed-forward neural networks2013
- A Field Programmable Neural Array2006