94 citations · 150 across the 6 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
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★ 2 cited
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…