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.
|Number of pages||5|
|Journal||IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems|
|Publication status||Published - 2019 Nov|
Bibliographical noteFunding Information:
Manuscript received October 13, 2017; revised December 26, 2017; accepted February 6, 2018. Date of publication October 25, 2018; date of current version October 16, 2019. This work was supported in part by the Basic Science Research Program through the National Research Foundation of Korea funded by the Ministry of Education under Grant NRF-2017R1D1A1B03029103, and in part by the Institute for Information and Communications Technology Promotion funded by the Korea Government under Grant 1711073912. This paper was recommended by Associate Editor C. H. Chang.
© 1982-2012 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design
- Electrical and Electronic Engineering