Structured Learning Team Seminar (Dr. Matthias Weissenbacher)

Structured Learning Team
This is an online seminer. Registration is required.
We’ll send the instruction for attending the online seminar.

Date: 2020-06-17 15:30-16:30
Speaker:Dr. Matthias Weissenbacher

【Title】Temporally Folded Convolutional Neural Networks for Sequence Forecasting

【Abstract】 In this work we propose a novel approach to utilize convolutional neural networks for time series
forecasting. We empirically compare our strategy to LSTM’s and convolutional LSTM’s on their performance
on the sequential MNIST and the JSB Chorals dataset, respectively. We conclude that the proposed
"temporally folded" CNN’s can outperform the conventional recurrent strategies.