In:
Neuromorphic Computing and Engineering, IOP Publishing, Vol. 2, No. 3 ( 2022-09-01), p. 034006-
Abstract:
Overfitting is a common and critical challenge for neural networks trained with limited dataset. The conventional solution is software-based regularization algorithms such as Gaussian noise injection. Semiconductor noise, such as 1/ f noise, in artificial neuron/synapse devices, which is often regarded as undesirable disturbance to the hardware neural networks (HNNs), could also play a useful role in suppressing overfitting, but that is as yet unexplored. In this work, we proposed the idea of using 1/ f noise injection to suppress overfitting in different neural networks, and demonstrated that: (i) 1/ f noise could suppress the overfitting in multilayer perceptron (MLP) and long short-term memory (LSTM); (ii) 1/ f noise and Gaussian noise performs similarly for the MLP but differently for the LSTM; (iii) the superior performance of 1/ f noise on LSTM can be attributed to its intrinsic long range dependence. This work reveals that 1/ f noise, which is common in semiconductor devices, can be a useful solution to suppress the overfitting in HNNs, and more importantly, further evidents that the imperfectness of semiconductor devices is a rich mine of solutions to boost the development of brain-inspired hardware technologies in the artificial intelligence era.
Type of Medium:
Online Resource
ISSN:
2634-4386
DOI:
10.1088/2634-4386/ac6d05
Language:
Unknown
Publisher:
IOP Publishing
Publication Date:
2022
detail.hit.zdb_id:
3099608-9