(Deep) Neural networks through evolution

0 0

Neural networks, including the popular "deep" networks, are useful tools for learning from data or from interactions. Typically, neural networks are trained with gradient descent. However, it is very hard to find gradients in very deep networks, or in the structure of the networks itself. Evolutionary algorithms can train neural network weights and structures through a process inspired by Darwinian evolution. I will give an introduction to the ideas behind neuroevolution, and discuss some applications in games, robotics and computer vision.

Øredev 2017

Øredev is the perfect blend, with one day of in-depth pre-conference workshops and three days of sessions, you will get tons of inspiration and learning to keep you creating your best work all year...