The future has arrived

In the last couple of years, deep learning techniques have transformed the world of artificial intelligence. One by one, the abilities and techniques that humans once imagined were uniquely our own have begun to fall to the onslaught of ever more powerful machines. 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. Deep neural networks are now better than humans at tasks such as face recognition and object recognition. They’ve mastered the ancient game of Go and thrashed the best human players. Nevertheless "continual learning poses particular challenges for artificial neural networks due to the tendency for knowledge of the previously learned task(s) (e.g., task A) to be abruptly lost as information relevant to the current task (e.g., task B) is incorporated." Well, NOT ANYMORE!!!! Researchers have now 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. Developed by Google’s AI company, DeepMind, the program has taken on a range of different tasks and performed almost as well as a human. Crucially, and uniquely, the AI does not forget how it solved past problems, and uses the knowledge to tackle new ones. Read all about: https://www.theguardian.com/global/2017/mar/14/googles-deepmind-makes-ai-program-that-can-learn-like-a-human#img-1 Or go deeper and read the published research article at: http://www.pnas.org/content/early/2017/03/13/1611835114.full.pdf

#AI #physics #Future