94 citations · 164 across the 18 of their papers we have counts for
4 papers · 1 filter
Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting
Craig Atkinson, Brendan McCane, Lech Szymanski +1
Neural networks can achieve excellent results in a wide variety of applications. However, when they attempt to sequentially learn, they tend to learn the new task while catastrophi…
The effect of the choice of neural network depth and breadth on the size of its hypothesis space
Lech Szymanski, Brendan McCane, Michael Albert
We show that the number of unique function mappings in a neural network hypothesis space is inversely proportional to , where is the number of neurons in the h…
Some Approximation Bounds for Deep Networks
Brendan McCane, Lech Szymanski
In this paper we introduce new bounds on the approximation of functions in deep networks and in doing so introduce some new deep network architectures for function approximation. T…
Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks
Craig Atkinson, Brendan McCane, Lech Szymanski +1
In general, neural networks are not currently capable of learning tasks in a sequential fashion. When a novel, unrelated task is learnt by a neural network, it substantially forget…