D
Dylan Banarse
Researcher at Google
Publications - 12
Citations - 885
Dylan Banarse is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Time delay neural network. The author has an hindex of 7, co-authored 10 publications receiving 673 citations. Previous affiliations of Dylan Banarse include See's Candies & Bangor University.
Papers
More filters
Posted Content
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
Chrisantha Fernando,Dylan Banarse,Charles Blundell,Yori Zwols,David Ha,Andrei Rusu,Alexander Pritzel,Daan Wierstra +7 more
TL;DR: Successful transfer learning is demonstrated; fixing the parameters along a path learned on task A and re-evolving a new population of paths for task B, allows task B to be learned faster than it could be learned from scratch or after fine-tuning.
Posted Content
Convolution by Evolution: Differentiable Pattern Producing Networks
Chrisantha Fernando,Dylan Banarse,Malcolm Reynolds,Frederic Besse,David Pfau,Max Jaderberg,Marc Lanctot,Daan Wierstra +7 more
TL;DR: In this paper, a differentiable version of the Compositional Pattern Producing Network, called the DPPN, is introduced, which can be evolved/trained to compress the weights of a denoising autoencoder from 157684 to roughly 200 parameters.
Proceedings ArticleDOI
Convolution by Evolution: Differentiable Pattern Producing Networks
Chrisantha Fernando,Dylan Banarse,Malcolm Reynolds,Frederic Besse,David Pfau,Max Jaderberg,Marc Lanctot,Daan Wierstra +7 more
TL;DR: In this article, a differentiable version of the Compositional Pattern Producing Network, called the DPPN, is introduced, which can be evolved/trained to compress the weights of a denoising autoencoder from 157684 to roughly 200 parameters.
Proceedings ArticleDOI
Deformation invariant pattern classification for recognising hand gestures
Dylan Banarse,A.W.G. Duller +1 more
TL;DR: A three stage self-organising neural network architecture has been developed to perform recognition of static hand gestures from images and is successfully applied to a set of hand gestures by selecting network parameters according to a sets of heuristic rules.
Journal ArticleDOI
Analysis and application of a self-organising image recognition neural network
Dylan Banarse,A.W.G. Duller +1 more
TL;DR: The feature extraction methods investigated are oriented Gaussian filters, Gabor filters and oriented Laplacian of Gaussian (L∘G) filters, which are shown to compare favourably with other techniques designed specifically for the two tasks.