Algoritmos de computación

Previous versions of AlphaGo initially trained on thousands of human amateur and professional games to learn how to play Go. AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play. In doing so, it quickly surpassed human level of play and defeated the previously published champion-defeating version of AlphaGo by 100 games to 0. If similar techniques can be applied to other structured problems, such as protein folding, reducing energy consumption or searching for revolutionary new materials, the resulting breakthroughs have the potential to positively impact society.  (Profesor David Silver) ¡Realmente increíble las implicaciones que tiene este descubrimiento de   DeepMind ! Su modelo neuronal   AlphaGo Zero   es capaz de aprender SOLO sin necesitar de datos de ningún tipo (ya no necesita siquiera aprender de jugadas de humanos como su versión anterior); simplemente aprende jugando contra sí mismo. ...