1 citations · 1 across the 3 of their papers we have counts for
6 papers · 1 filter
Conceptual capacity and effective complexity of neural networks
Lech Szymanski, Brendan McCane, Craig Atkinson
We propose a complexity measure of a neural network mapping function based on the diversity of the set of tangent spaces from different inputs. Treating each tangent space as a lin…
MIME: Mutual Information Minimisation Exploration
Haitao Xu, Brendan McCane, Lech Szymanski +1
We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to lea…
GRIm-RePR: Prioritising Generating Important Features for Pseudo-Rehearsal
Craig Atkinson, Brendan McCane, Lech Szymanski +1
Pseudo-rehearsal allows neural networks to learn a sequence of tasks without forgetting how to perform in earlier tasks. Preventing forgetting is achieved by introducing a generati…
Switched linear projections for neural network interpretability
Lech Szymanski, Brendan McCane, Craig Atkinson
We introduce switched linear projections for expressing the activity of a neuron in a deep neural network in terms of a single linear projection in the input space. The method work…
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…
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…