Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Stochastic Tucker-Decomposed Recurrent Neural Networks for Forecasting

Abstract: 

The growing edge computing paradigm, notably the vision of the internet-of-things (IoT), calls for a new epitome of lightweight algorithms. Currently, the most successful models that learn from temporal data, which is prevalent in IoT applications, stem from the field of deep learning. However, these models evince extended training times and heavy resource requirements, prohibiting training in constrained environments. To address these concerns, we employ deep stochastic neural networks from the reservoir computing paradigm. These networks train quickly with no need for backpropagation and we further accelerate training by employing Tucker decomposition. We demonstrate that such networks benefit from both tensorization and compression, and achieve a reduction of FLOPs up to ~95% while outperforming the uncompressed counterparts.

up
0 users have voted:

Paper Details

Authors:
Zachariah Carmichael, Dhireesha Kudithipudi
Submitted On:
29 October 2019 - 2:12pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Zachariah Carmichael
Paper Code:
1570570141
Document Year:
2019
Cite

Document Files

Presentation Slides

(110)

Subscribe

[1] Zachariah Carmichael, Dhireesha Kudithipudi, "Stochastic Tucker-Decomposed Recurrent Neural Networks for Forecasting", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4899. Accessed: Sep. 20, 2020.
@article{4899-19,
url = {http://sigport.org/4899},
author = {Zachariah Carmichael; Dhireesha Kudithipudi },
publisher = {IEEE SigPort},
title = {Stochastic Tucker-Decomposed Recurrent Neural Networks for Forecasting},
year = {2019} }
TY - EJOUR
T1 - Stochastic Tucker-Decomposed Recurrent Neural Networks for Forecasting
AU - Zachariah Carmichael; Dhireesha Kudithipudi
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4899
ER -
Zachariah Carmichael, Dhireesha Kudithipudi. (2019). Stochastic Tucker-Decomposed Recurrent Neural Networks for Forecasting. IEEE SigPort. http://sigport.org/4899
Zachariah Carmichael, Dhireesha Kudithipudi, 2019. Stochastic Tucker-Decomposed Recurrent Neural Networks for Forecasting. Available at: http://sigport.org/4899.
Zachariah Carmichael, Dhireesha Kudithipudi. (2019). "Stochastic Tucker-Decomposed Recurrent Neural Networks for Forecasting." Web.
1. Zachariah Carmichael, Dhireesha Kudithipudi. Stochastic Tucker-Decomposed Recurrent Neural Networks for Forecasting [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4899