643 citations · 1.2k across the 13 of their papers we have counts for
5 papers · 1 filter
Meta-Learning by the Baldwin Effect
Chrisantha Thomas Fernando, Jakub Sygnowski, Simon Osindero +6
The scope of the Baldwin effect was recently called into question by two papers that closely examined the seminal work of Hinton and Nowlan. To this date there has been no demonstr…
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
Chrisantha Fernando, Dylan Banarse, Charles Blundell +5
For artificial general intelligence (AGI) it would be efficient if multiple users trained the same giant neural network, permitting parameter reuse, without catastrophic forgetting…
Convolution by Evolution: Differentiable Pattern Producing Networks
Chrisantha Fernando, Dylan Banarse, Malcolm Reynolds +5
In this work we introduce a differentiable version of the Compositional Pattern Producing Network, called the DPPN. Unlike a standard CPPN, the topology of a DPPN is evolved but th…
Learning to Generate Genotypes with Neural Networks
Alexander W. Churchill, Siddharth Sigtia, Chrisantha Fernando
Neural networks and evolutionary computation have a rich intertwined history. They most commonly appear together when an evolutionary algorithm optimises the parameters and topolog…
A Denoising Autoencoder that Guides Stochastic Search
Alexander W. Churchill, Siddharth Sigtia, Chrisantha Fernando
An algorithm is described that adaptively learns a non-linear mutation distribution. It works by training a denoising autoencoder (DA) online at each generation of a genetic algori…