How human learning can foster smarter artificial intelligence

Researchers, including one of Indian-origin, have given a new insight into how human learning can foster smarter artificial intelligence.
Recent breakthroughs in creating artificial systems that outplay humans in a diverse array of challenging games have their roots in neural networks inspired by information processing in the brain, researchers said.
Now, scientists from Google DeepMind and Stanford University in the US have updated a theory originally developed to explain how humans and other animals learn - and highlight its potential importance as a framework to guide the development of agents with artificial intelligence.
First published in 1995, the theory states that learning is the product of two complementary learning systems.

The first system gradually acquires knowledge and skills from exposure to experiences, and the second stores specific experiences so that these can be replayed to allow their effective integration into the first system, researchers said.
"The evidence seems compelling that the brain has these two kinds of learning systems, and the complementary learning systems theory explains how they complement each other to provide a powerful solution to a key learning problem that faces the brain," said James McClelland from Stanford University.

The first system in the proposed theory, placed in the neocortex of the brain, was inspired by precursors of today's deep neural networks. As with today's deep networks, these systems contain several layers of neurons between input and output, and the knowledge in these networks is in their connections, researchers said.

Their connections are gradually programmed by experience, giving rise to their ability to recognise objects, perceive speech, understand and produce language, and even to select optimal actions in game-playing and other settings where intelligent action depends on acquired knowledge.
Such systems face a dilemma when new information must be learned - if large enough changes are made to the connections to force the new knowledge into the connections quickly, it will radically distort all of the other knowledge already stored in the connections.
"That is where the complementary learning system comes in. By initially storing information about the new experience in the hippocampus, we make it available for immediate use and we also keep it around so that it can be replayed back to the cortex, interleaving it with ongoing experience and stored information from other relevant experiences," said McClelland.

"Components of the neural network architecture that succeeded in achieving human-level performance in a variety of computer games like Space Invaders and Breakout were inspired by complementary learning systems theory," said Dharshan Kumaran from Stanford University.
"As in the theory, these neural networks exploit a memory buffer akin to the hippocampus that stores recent episodes of game play and replays them in interleaved fashion," he said.
The findings were published in the journal Trends in Cognitive Sciences.