C
Chrisantha Fernando
Researcher at Google
Publications - 69
Citations - 3384
Chrisantha Fernando is an academic researcher from Google. The author has contributed to research in topics: Population & Evolutionary algorithm. The author has an hindex of 23, co-authored 68 publications receiving 2834 citations. Previous affiliations of Chrisantha Fernando include Queen Mary University of London & Central European 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.
Proceedings Article
Hierarchical Representations for Efficient Architecture Search
TL;DR: In this article, a hierarchical genetic representation scheme was used to discover architectures for image classification, achieving a top-1 accuracy of 3.6% on CIFAR-10 and 20.3% on ImageNet.
Journal ArticleDOI
Evolution before genes
Vera Vasas,Vera Vasas,Chrisantha Fernando,Chrisantha Fernando,Mauro Santos,Stuart A. Kauffman,Eörs Szathmáry,Eörs Szathmáry +7 more
TL;DR: It is discovered that if general conditions are satisfied, the accumulation of adaptations in chemical reaction networks can occur, and only when a chemical reaction network consists of many viable cores, can it be evolvable.
Posted Content
Hierarchical Representations for Efficient Architecture Search
TL;DR: This work efficiently discovers architectures that outperform a large number of manually designed models for image classification, obtaining top-1 error of 3.6% on CIFAR-10 and 20.3% when transferred to ImageNet, which is competitive with the best existing neural architecture search approaches.
Book ChapterDOI
Pattern Recognition in a Bucket
TL;DR: This paper demonstrates that the waves produced on the surface of water can be used as the medium for a “Liquid State Machine” that pre-processes inputs so allowing a simple perceptron to solve the XOR problem and undertake speech recognition.