A very old proposition has said that if only we could make a system as inquisitive as a child, and had it able to learn and extend its knowledge, we could get to intelligent machines. An ultimate form of Machine learning. We are not close to that, but the attempt continues. I like the term: Exploring Exploration. Bair takes a look and explains the idea and what is being done. So how do children explore to learn? And can we use that as a model for machines? Extensive and not too technical report.
Exploring Exploration: Comparing Children with RL Agents in Unified Environments
Eliza Kosoy, Jasmine Collins and David Chan Jul 24, 2020
Despite recent advances in artificial intelligence (AI) research, human children are still by far the best learners we know of, learning impressive skills like language and high-level reasoning from very little data. Children’s learning is supported by highly efficient, hypothesis-driven exploration: in fact, they explore so well that many machine learning researchers have been inspired to put videos like the one below in their talks to motivate research into exploration methods. However, because applying results from studies in developmental psychology can be difficult, this video is often the extent to which such research actually connects with human cognition. ... "
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment