Artificial intelligence has made great strides. If in the 1950s AIs played checkers, today sophisticated automated assistants can answer all kinds of questions and generate any kind of image, video or text.
Despite this evolution, AIs are still little flexible in learning from situations outside their programming. Their development could lead to a new era of artificial intelligence, the era of Neuromorphic Computation. It all begins with the so-called von Neumann machine model, a structure consisting of a memory storing information, a processor processing information, and a control unit with instructions for the other two. The operation of these elements produces the outputs of artificial intelligence.
The natural evolution of this functioning is the development of hardware and software imitating the structures and functions of the human brain and its network of neurons. Thus, neuromorphic chips, actual processors built to take advantage of some of the benefits of the human mind, were developed. Image recognition, autonomous driving and natural language processing are just some of the areas that would make giant leaps forward.
Learn more about neuromorphic computers in the sixth episode of What A Digital World!