A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks
- Kenneth O. Stanley, David B. D'Ambrosio, J. Gauci
- Biology, Computer ScienceArtificial Life
- 1 April 2009
The main conclusion is that the ability to explore the space of regular connectivity patterns opens up a new class of complex high-dimensional tasks to neuroevolution.
Autonomous Evolution of Topographic Regularities in Artificial Neural Networks
This letter shows that when geometry is introduced to evolved ANNs through the hypercube-based neuroevolution of augmenting topologies algorithm, they begin to acquire characteristics that indeed are reminiscent of biological brains.
Generating large-scale neural networks through discovering geometric regularities
- J. Gauci, Kenneth O. Stanley
- Computer Science, BiologyAnnual Conference on Genetic and Evolutionary…
- 7 July 2007
A method, called Hypercube-based Neuroevolution of Augmenting Topologies (HyperNEAT), which evolves a novel generative encoding called connective Compositional Pattern Producing Networks (connective CPPNs) to discover geometric regularities in the task domain, allowing the solution to both generalize and scale without loss of function to an ANN of over eight million connections.
Horizon: Facebook's Open Source Applied Reinforcement Learning Platform
Facebook's open source applied reinforcement learning (RL) platform Horizon is presented, which contains workflows to train popular deep RL algorithms and includes data preprocessing, feature transformation, distributed training, counterfactual policy evaluation, optimized serving, and a model-based data understanding tool.
A Case Study on the Critical Role of Geometric Regularity in Machine Learning
It is argued that geometric information is critical to the ability of any machine learning approach to effectively generalize; even a small shift in the configuration of the task in space from what was experienced in training can go wholly unrecognized unless the algorithm is able to learn the regularities in decision-making across the problem geometry.
Indirect Encoding of Neural Networks for Scalable Go
The scalable method is demonstrated to learn faster and ultimately discover better strategies than the same method trained on 7×7 Go directly from the start.
HyperNEAT: The First Five Years
This chapter reviews these first 5 years of research that builds upon this approach, and culminates with thoughts on promising future directions.
Obstacle Detection around Aircraft on Ramps and Taxiways through the use of Computer Vision
An onboard non-collaborative system to detect and track generic obstacles around the wingtips of large transport aircraft when maneuvering on ramps and taxiways and it is shown that stereo vision is the most appropriate technology for this application.
Evolving neural networks for geometric game-tree pruning
- J. Gauci, Kenneth O. Stanley
- Computer ScienceAnnual Conference on Genetic and Evolutionary…
- 12 July 2011
Geometric Game-Tree Pruning (GGTP), a novel evolutionary method that learns to prune game trees based on geometric properties of the game board, is discussed.
Real-Time Multiplayer Network Programming
Adding multiplayer support to a game increases the range of experiences that a player can have by introducing the elements of human psychology and social interaction to the game agents.