Efficient Recurrent Neural Networks using Structured Matrices in FPGAs

ICLR, Volume abs/1803.07661, 2018.

Cited by: 8|Views13
EI

Abstract:

Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The recent pruning based work ESE suffers from degradation of performance/energy efficiency due to the irregular network structure after pruning. We propose block-circulant matric...More

Code:

Data:

Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments