The proposed model represents a pioneering approach in traffic research by employing pure convolutional layers (TCN) to simultaneously extract spatial-temporal information from time series of graph ...

This is an experiment that tried to analyse the inception behind inception net. That is, factorising the convolutions. Can a sequence of nx1 -> 1xn convolution be more efficient than a single nxn ...

Abstract: In photovoltaic power forecasting, problems such as seasonal characteristics change and insufficient historical data are often faced. And because of the randomness of actual weather changes, ...

The Temporal Convolution Machine (TCM) is a neural architecture for learning temporal sequences that generalizes the Temporal Restricted Boltzmann Machine (TRBM). A convolution function is used to ...