LiteLSTM Architecture for Deep Recurrent Neural Networks

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware aspects. This paper proposes a novel LiteLSTM architecture b...

Full description

Saved in:
Bibliographic Details
Main Authors: Elsayed, Nelly, ElSayed, Zag, Maida, Anthony S.
Format: Conference Proceeding
Language:English
Subjects:
CO2 footprint
Computer architecture
GRU
Hardware
LiteLSTM
Logic gates
LSTM
MNIST
Performance evaluation
Recurrent neural networks
Software
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware aspects. This paper proposes a novel LiteLSTM architecture based on reducing the computation components of the LSTM using the weights sharing concept to reduce the overall architecture cost and maintain the architecture performance. The proposed LiteLSTM can be significant for learning big data where time-consumption is crucial such as the security of IoT devices and medical data. Moreover, it helps to reduce the CO2 footprint. The proposed model was evaluated and tested empirically on two different datasets from computer vision and cybersecurity domains.
ISSN:2158-1525
DOI:10.1109/ISCAS48785.2022.9937585