Optogenetics inspired transition metal dichalcogenide neuristors for in-memory deep recurrent neural networks
Open Access
- 25 June 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in Nature Communications
- Vol. 11 (1), 1-9
- https://doi.org/10.1038/s41467-020-16985-0
Abstract
Shallow feed-forward networks are incapable of addressing complex tasks such as natural language processing that require learning of temporal signals. To address these requirements, we need deep neuromorphic architectures with recurrent connections such as deep recurrent neural networks. However, the training of such networks demand very high precision of weights, excellent conductance linearity and low write-noise- not satisfied by current memristive implementations. Inspired from optogenetics, here we report a neuromorphic computing platform comprised of photo-excitable neuristors capable of in-memory computations across 980 addressable states with a high signal-to-noise ratio of 77. The large linear dynamic range, low write noise and selective excitability allows high fidelity opto-electronic transfer of weights with a two-shot write scheme, while electrical in-memory inference provides energy efficiency. This method enables implementing a memristive deep recurrent neural network with twelve trainable layers with more than a million parameters to recognize spoken commands with >90% accuracy.Funding Information
- Ministry of Education - Singapore (RG 166/16, MOE2015-T2-2-007, MOE2015-T2-2-043, MOE2017-T2-2-136, MOE2016-T2-1-100)
This publication has 51 references indexed in Scilit:
- Deep learningNature, 2015
- Training and operation of an integrated neuromorphic network based on metal-oxide memristorsNature, 2015
- Optogenetics: the age of lightNature Methods, 2014
- A million spiking-neuron integrated circuit with a scalable communication network and interfaceScience, 2014
- Ultrasensitive photodetectors based on monolayer MoS2Nature Nanotechnology, 2013
- Optogenetic manipulation of neural circuits and behavior in Drosophila larvaeNature Protocols, 2012
- Gated three-terminal device architecture to eliminate persistent photoconductivity in oxide semiconductor photosensor arraysNature Materials, 2012
- Millisecond-timescale, genetically targeted optical control of neural activityNature Neuroscience, 2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Long Short-Term MemoryNeural Computation, 1997