Communications of the ACM
The Computer Scientist Training AI to Think With Analogies
"You've already lost the battle if you're having to train [AI] on thousands and thousands of examples. That's not what abstraction is all about. It's all about what people in machine learning call 'few-shot learning,' which means you learn on a very small
Melanie Mitchell is the Davis Professor at the Santa Fe Institute. Her current research focuses on conceptual abstraction, analogy-making, and visual recognition in AI systems.
Melanie Mitchell believes that making analogies—allowing AI systems to apply existing knowledge to new problems—will help them truly understand the data they're manipulating.
"It is a fundamental mechanism of thought that will help AI get to where we want it to be," she says in an interview.
"Some people say that being able to predict the future is what's key for AI, or being able to have common sense, or the ability to retrieve memories that are useful in a current situation. But, in each of these things, analogy is very central."
From Quanta Magazine
View Full Article
No entries found