Bayesian Incremental Learning for Deep Neural Networks

no code implementations • 20 Feb 2018 • Max Kochurov, Timur Garipov, Dmitry Podoprikhin, Dmitry Molchanov, Arsenii Ashukha, Dmitry Vetrov

In industrial machine learning pipelines, data often arrive in parts.

Incremental Learning

Ultimate tensorization: compressing convolutional and FC layers alike

2 code implementations • 10 Nov 2016 • Timur Garipov, Dmitry Podoprikhin, Alexander Novikov, Dmitry Vetrov

Convolutional neural networks excel in image recognition tasks, but this comes at the cost of high computational and memory complexity.

Tensorizing Neural Networks

4 code implementations • NeurIPS 2015 • Alexander Novikov, Dmitry Podoprikhin, Anton Osokin, Dmitry Vetrov

Deep neural networks currently demonstrate state-of-the-art performance in several domains.

Image Classification