Azalia Mirhoseini, a research scientist at Google Brain, is using artificial intelligence itself to make better chips for artificial intelligence.Many microchips that are used for Al weren't specifically built for it. Most are repur-posed from hardware used in video and gaming. As a result, these older, human-engineered designs leave much to be desired in terms of energy efficiency, cost, and functionality.Mirhoseini's system -which trained itself using trial and error, based on the Al concept of reinforcement learning - can produce chip designs in just a few hours. (The world's top experts need several weeks.) Her Al-designed methods allow for chips that are as good as or better than those designed by human engineers: they're faster, more energy efficient, and much cheaper.Reinforcement learning is one of Al's most promising frameworks. Software that uses it essentially teaches itself how to accomplish a task, rather than being programmed, step by step, by a human. Now, Mirhoseini says, "it's time to use machine learning and Al to develop better computers and close the loop."
展开▼