581 citations · 1.8k across the 41 of their papers we have counts for
Showing 2016 · cs.LGShow all
3 papers · 2 filters
cs.LG2016★ 5 cited
Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks
David Balduzzi, Brian McWilliams, Tony Butler-Yeoman
Modern convolutional networks, incorporating rectifiers and max-pooling, are neither smooth nor convex; standard guarantees therefore do not apply. Nevertheless, methods from conve…
cs.LG2016★ 5 cited
Deep Online Convex Optimization with Gated Games
David Balduzzi
Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolu…
cs.LG2016★ 15 cited
Strongly-Typed Recurrent Neural Networks
David Balduzzi, Muhammad Ghifary
Recurrent neural networks are increasing popular models for sequential learning. Unfortunately, although the most effective RNN architectures are perhaps excessively complicated, e…