Memory level neural network: A time-varying neural network for memory input processing

Affective computing is an important foundation for implementing brain-like computing and advanced machine intelligence. However, the instantaneous and memory fusion input characteristic makes current neural networks not suitable for affective computing. In this paper, we propose an affective computi...

Full description

Saved in:

Bibliographic Details
Published in:	Neurocomputing (Amsterdam) Vol. 425; pp. 256 - 265
Main Authors:	Gong, Chao, Zhou, Xianwei, Lü, Xing, Lin, Fuhong
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 15.02.2021
Subjects:	Affective computing Memory level neuron Memory level transition MLNN Time-related memory input Time-varying output Affective computing Memory level transition MLNN Memory level neuron Time-varying output Time-related memory input
ISSN:	0925-2312, 1872-8286
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Affective computing is an important foundation for implementing brain-like computing and advanced machine intelligence. However, the instantaneous and memory fusion input characteristic makes current neural networks not suitable for affective computing. In this paper, we propose an affective computing oriented memory level neural network. A “switch” has been added to the memory level neurons, which will achieve a transition from the instantaneous input to the memory input when the temporal integration of inputs above a certain threshold. Then, the “switch” is continualized by an adjustable sigmoid function whose parameters are tuned to adjust the speed of the transition and the mixing ratio of the two inputs. Multiple memory level neurons form a deep time-varying neural network capable of handling fusional inputs. We demonstrate on both process datasets and static datasets that the memory level neural network successfully converges on both datasets and meets the error accuracy requirements.
ISSN:	0925-2312 1872-8286
DOI:	10.1016/j.neucom.2020.04.093