LogicWiSARD: Memoryless Synthesis of Weightless Neural Networks

Weightless neural networks (WNNs) are an alternative pattern recognition technique where RAM nodes function as neurons. As both training and inference require mostly table lookups, few additions, and no multiplications, WNNs are suitable for high-performance and low-power embedded applications. This...

Full description

Saved in:
Bibliographic Details
Main Authors: Miranda, Igor D.S., Arora, Aman, Susskind, Zachary, Villon, Luis A.Q., Katopodis, Rafael F., Dutra, Diego L.C., De Araujo, Leandro S., Lima, Priscila M.V., Franca, Felipe M.G., John, Lizy K., Breternitz, Mauricio
Format: Conference Proceeding
Language:English
Subjects:
FPGA
Logic functions
Neurons
Program processors
Random access memory
Systems architecture
Table lookup
Training
VLSI
Weightless neural networks
WiSARD
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Weightless neural networks (WNNs) are an alternative pattern recognition technique where RAM nodes function as neurons. As both training and inference require mostly table lookups, few additions, and no multiplications, WNNs are suitable for high-performance and low-power embedded applications. This work introduces a novel approach to implement WiSARD, the leading WNN state-of-the-art architecture, completely eliminating memories and arithmetic circuits and utilizing only logic functions. The approach creates compressed minimized implementations by converting trained WNN nodes from lookup tables to logic functions. The proposed LogicWiSARD is implemented in FPGA and ASIC technologies to illustrate its suitability for edge inference. Experimental results show more than 80% reduction in energy consumption when the proposed LogicWiSARD model is compared with a multilayer perceptron network (MLP) of equivalent accuracy. Compared to previous work on FPGA implementations for WNNs, convolutional neural networks, and binary neural networks, the energy savings of LogicWiSARD range between 32.2% and 99.6%.
ISSN:2160-052X
DOI:10.1109/ASAP54787.2022.00014