- Collaborative Evolutionary Reinforcement Learning - Jul 8, 2019.
Intel Researchers created a new approach to RL via Collaborative Evolutionary Reinforcement Learning (CERL) that combines policy gradient and evolution methods to optimize, exploit, and explore challenges.
- Evolving Deep Neural Networks - Jun 18, 2019.
This article reviews how evolutionary algorithms have been proposed and tested as a competitive alternative to address a number of issues related to neural network design.
- Large-Scale Evolution of Image Classifiers - May 16, 2019.
Deep neural networks excel in many difficult tasks, given large amounts of training data and enough processing power. The neural network architecture is an important factor in achieving a highly accurate model... Techniques to automatically discover these neural network architectures are, therefore, very much desirable.
- Evolutionary Algorithms for Feature Selection - Nov 29, 2017.
Feature selection is a very important technique in machine learning. In this post we discuss one of the most common optimization algorithms for multi-modal fitness landscapes - evolutionary algorithms.
- Deep Learning can be easily fooled - Jan 14, 2015.
It is almost impossible for human eyes to label the images below to be anything but abstract arts. However, researchers found that Deep Neural Network will label them to be familiar objects with 99.99% confidence. The generality of DNN is questioned again.
- DEAP, Distributed Evolutionary Algorithms in Python, Framework for Rapid Prototyping - Feb 20, 2014.
DEAP is a novel evolutionary computation framework for rapid prototyping and testing of ideas, seeking to make algorithms explicit and data structures transparent. Free Download.