Title
An On-Chip Learning Neuromorphic Autoencoder With Current-Mode Transposable Memory Read and Virtual Lookup Table.
Abstract
This paper presents an IC implementation of on-chip learning neuromorphic autoencoder unit in a form of rate-based spiking neural network. With a current-mode signaling scheme embedded in a 500 × 500 6b SRAM-based memory, the proposed architecture achieves simultaneous processing of multiplications and accumulations. In addition, a transposable memory read for both forward and backward propagation...
Year
DOI
Venue
2018
10.1109/TBCAS.2017.2762002
IEEE Transactions on Biomedical Circuits and Systems
Keywords
Field
DocType
Neurons,Hardware,System-on-chip,Neuromorphics,Computer architecture,Pulse width modulation
Restricted Boltzmann machine,Lookup table,Autoencoder,MNIST database,Computer science,Neuromorphic engineering,Electronic engineering,Computational science,Unsupervised learning,Spiking neural network,Synaptic weight
Journal
Volume
Issue
ISSN
12
1
1932-4545
Citations 
PageRank 
References 
1
0.37
0
Authors
6
Name
Order
Citations
PageRank
Hwasuk Cho123.12
Hyunwoo Son2114.43
Kihwan Seong312.39
Byungsub Kim416537.71
Hong-june Park546572.93
Jae-yoon Sim650883.58