Quaternion Neural Networks for Sequence Classification

Authors

Presenter(s)

Cameron E Long

Files

Description

Recently the field of deep learning has made significant advancement, included in this category is the subject of sequence classification. Recent research has shown that traditional sequence processing deep learning architectures such as the Long Short-Term Memory cell (LSTM) or the Gated Recurrent Unit (GRU) can be replaced by Dilated Fully Convolutional Networks called a Temporal Convolutional Network (TCN). Other research has shown that by representing deep networks with complex and quaternion numbers, the networks tend to show improved convergence while using significantly less learned parameters. We combine these two observations to create a Quaternion Temporal Convolution Network (QTCN), and show its performance on sequential classification tasks.

Publication Date

4-24-2019

Project Designation

Graduate Research

Primary Advisor

Vijayan K. Asari

Primary Advisor's Department

Electrical and Computer Engineering

Keywords

Stander Symposium project

Recommended Citation

"Quaternion Neural Networks for Sequence Classification" (2019). Stander Symposium Projects. 1447.
https://ecommons.udayton.edu/stander_posters/1447