For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Dynamic Fixed-Point Design of Neuromorphic Computing Systems
Yongshin KANG Jaeyong CHUNG
IEICE TRANSACTIONS on Electronics
Publication Date: 2018/10/01
Online ISSN: 1745-1353
Type of Manuscript: BRIEF PAPER
Category: Microwaves, Millimeter-Waves
neural network, machine learning, VLSI,
Full Text: PDF(348.7KB)
>>Buy this Article
Practical deep neural networks have a number of weight parameters, and the dynamic fixed-point formats have been used to represent them efficiently. The dynamic fixed-point representations share an scaling factor among a group of numbers, and the weights in a layer have been formed into such a group. In this paper, we first explore a design space for dynamic fixed-point neuromorphic computing systems and show that it is indispensable to have a small group size in neuromorphic architectures, because it is appropriate to group the weights associated with a neuron into a group. We then presents a dynamic fixed-point representation designed for neuromorphic computing systems. Our experimental results show that the proposed representation reduces the required weight bitwidth by about 4 bits compared to the conventional fixed-point format.