An artificial-intelligence algorithm that discovers its own way to learn achieves state-of-the-art performance, including on some tasks it had never encountered before. Joel Lehman is at Lila Sciences ...

AI R&D runs on a cycle of hypothesis, experiment, and analysis — each step demanding substantial manual engineering effort. A new framework from researchers at SII-GAIR aims to close that bottleneck ...

Genetic algorithms and the recombination problem Discussions around AI creativity often focus on neural networks, which require extensive computing infrastructure and massive training datasets.