The Guardian reports that Google’s DeepMind makes an artificial intelligence program that can learn like a human. The program brings artificial general intelligence a step closer by using previous knowledge to solve fresh problems.
The article in the The Guardian points out that the researchers have overcome one of the major stumbling blocks in artificial intelligence with a program that can learn one task after another using skills it acquires on the way. The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Until now neural networks have not been capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. Here you may read the research article.