Cameron E Long
Download Project (11.2 MB)
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.
Vijayan K. Asari
Primary Advisor's Department
Electrical and Computer Engineering
Stander Symposium project
"Quaternion Neural Networks for Sequence Classification" (2019). Stander Symposium Projects. 1447.