LEARNING ABSTRACTION WITH NEURAL NETWORKS
| David Ha at Eyeo 2018 |
David is a Research Scientist at Google Brain. His research interests include Recurrent Neural Networks, Creative AI, and Evolutionary Computing. In this talk he discusses some of his experience with getting neural networks to do interesting things, without clear useful goals in mind. In one example he shows how we can make a simple dataset interesting by getting a neural network to enlarge images without being explicitly being trained to do so. He also discusses the use of neural networks to generate vector sketches, and finally, to generate entire worlds.