Study Finds That Machines Can Learn Through Pattern Recognition

Machines can learn through pattern recognition. Both machine and human were asked to match a similar character written by somebody else. Although machines can conduct pattern replication tasks, they characteristically need to be given thousands of examples in order to perform them with the same level of accuracy as human beings. The journal science has published the machine learning by the researchers at the Massachusetts institute of technology, university of Toronto and the New York University. In a paper published n science nearly ten years ago with this doctoral advisor Geoffrey Hinton, Salakhutdinov helped a lot in launching the recent interest in learning with deep neural networks. In another main step forward in artificial intelligence research, computer scientists have developed an algorithm that allows computers to recognize simple visual concepts…


Link to Full Article: Study Finds That Machines Can Learn Through Pattern Recognition