activity
20182021
most citedConceptual capacity and effective complexity of neural networks

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG20211 cited

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…

cs.LG2020

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…

cs.LG2019

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…

cs.LG2019

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…

cs.LG2018

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…

cs.LG2018

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…