FaCT-LSTM: Fast and Compact Ternary Architecture for LSTM Recurrent Neural Networks

Seyed Ahmad Mirsalari, Najmeh Nazari, Sima Sinaei, Mostafa E. Salehi, Masoud Daneshtalab

IEEE Design and Test · 2021 · 12 citations · 4 references

Concepts

Abstract

This article proposes a Fast and Compact Ternary LSTM (FaCTLSTM), which bridges the accuracy gap between the full-precision and quantized neural networks.

References

4