activity
20162026
most citedPseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting

94 citations · 164 across the 18 of their papers we have counts for

collaborators
Showing 2017Show all

2 papers · 1 filter

cs.LG2017

Effects of the optimisation of the margin distribution on generalisation in deep architectures

Lech Szymanski, Brendan McCane, Wei Gao +1

Despite being so vital to success of Support Vector Machines, the principle of separating margin maximisation is not used in deep learning. We show that minimisation of margin vari…

cs.LG2017★ 10 cited

Deep Radial Kernel Networks: Approximating Radially Symmetric Functions with Deep Networks

Brendan McCane, Lech Szymanski

We prove that a particular deep network architecture is more efficient at approximating radially symmetric functions than the best known 2 or 3 layer networks. We use this architec…