Currently, Deep Learning Ensembles take a very long time to train, and are very expensive. This talk illustrates some of the steps that Alan has taken in his research in order to formulate new, faster Ensemble methods for Deep Learning, and how that has also led to general improvements in training single Deep Learning models.
YOU MAY ALSO LIKE:
Fast, scalable Deep Learning Ensembles
Alan Mosca is a part-time research student at Birkbeck, University of London. He also holds a full time position as Senior Data Engineer at Sendence. His research focus is on Deep Learning Ensembles and improvements to optimisation algorithms in Deep Learning. He was previously at Wadhwani Asset Management, Jane Street Capital, and several software companies.