Prof. Vasilaki quoted in New Scientist

Prof. Eleni Vasilaki has recently been quoted in the New Scientist on an article featuring Google's DeepMind.

The news article reports that Google DeepMind's AI has learned to play with physical objects, much like how children learn about the physical world.

The AI in the experiments was given a reward or negative feedback depending on its answer. This type of training is call reinforcement learning. “Reinforcement learning allows solving tasks without specific instructions, similar to how animals or humans are able to solve problems,” says Prof. Eleni Vasilaki. “As such, it can lead to the discovery of ingenious new ways to deal with known problems, or to finding solutions when clear instructions are not available.”

You can read the full article on the New Scientist web pages