643 citations · 1.2k across the 13 of their papers we have counts for
14 papers
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Chrisantha Fernando, Dylan Banarse, Henryk Michalewski +2
Popular prompt strategies like Chain-of-Thought Prompting can dramatically improve the reasoning abilities of Large Language Models (LLMs) in various domains. However, such hand-cr…
CLIP-CLOP: CLIP-Guided Collage and Photomontage
Piotr Mirowski, Dylan Banarse, Mateusz Malinowski +2
The unabated mystique of large-scale neural networks, such as the CLIP dual image-and-text encoder, popularized automatically generated art. Increasingly more sophisticated generat…
Generative Art Using Neural Visual Grammars and Dual Encoders
Chrisantha Fernando, S. M. Ali Eslami, Jean-Baptiste Alayrac +3
Whilst there are perhaps only a few scientific methods, there seem to be almost as many artistic methods as there are artists. Artistic processes appear to inhabit the highest orde…
From Language Games to Drawing Games
Chrisantha Fernando, Daria Zenkova, Stanislav Nikolov +1
We attempt to automate various artistic processes by inventing a set of drawing games, analogous to the approach taken by emergent language research in inventing communication game…
Evolving intrinsic motivations for altruistic behavior
Jane X. Wang, Edward Hughes, Chrisantha Fernando +3
Multi-agent cooperation is an important feature of the natural world. Many tasks involve individual incentives that are misaligned with the common good, yet a wide range of organis…
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…
Population Based Training of Neural Networks
Max Jaderberg, Valentin Dalibard, Simon Osindero +9
Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model a…
Hierarchical Representations for Efficient Architecture Search
Hanxiao Liu, Karen Simonyan, Oriol Vinyals +2
We explore efficient neural architecture search methods and show that a simple yet powerful evolutionary algorithm can discover new architectures with excellent performance. Our ap…
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…
Design for a Darwinian Brain: Part 2. Cognitive Architecture
Chrisantha Fernando, Vera Vasas
The accumulation of adaptations in an open-ended manner during lifetime learning is a holy grail in reinforcement learning, intrinsic motivation, artificial curiosity, and developm…
Design for a Darwinian Brain: Part 1. Philosophy and Neuroscience
Chrisantha Fernando
Physical symbol systems are needed for open-ended cognition. A good way to understand physical symbol systems is by comparison of thought to chemistry. Both have systematicity, pro…