An example of what the AI community is lacking and how can you learn from it?
--
A positive discovery but a startling negative that this had not been looked into so far
Long story short — “engineers at the company DeepMind built a machine-learning system based on research on how babies’ brain works, and it did better on certain tasks than its conventional counterparts”.
While this is a good positive it is bemusing to me that such outside-the-box thinking was absent from the community thus far. Am I being too skeptic? I don’t think so. We have had a lot of examples where multidisciplinary and lateral thinking yield far greater results and we haven’t adapted as much as we should.
Here is a piece of the transcript from the podcast for more context:
Christopher Intagliata: Artificial intelligence systems have bested humans at chess, poker, Jeopardy, Go, and countless other games. But machines still aren’t that great at understanding some basic rules about the physical world.
Susan Hespos: They still can’t do what 3-month-olds do. And I’m a champion for babies at the end of the day and this is a clear win for babies. Babies are still slam dunking our most powerful computers when it comes to intuitive physics.
Intagliata: Cognitive psychologist Susan Hespos of Northwestern University listed off a few examples of those “intuitive physics” principles. Like “solidity” — your coffee cup does not just fall right through the table. Or “continuity” — objects don’t just blink in and out of existence. And “boundedness” — when you pick up your coffee cup, it sticks together. You don’t end up with just the handle.
Hespos: Babies know all three of these things as early as three months of age. Their visual acuity is lousy, the world is blurry…they could barely grasp this stuff. You know, babies get a lot of things wrong. But it’s these initial kernels that get elaborated and refined through experience in the world.
Intagliata: Now computer engineers have taken a page from the baby playbook. Researchers at DeepMind — the AI company that trained computers to beat humans at Go — have endowed a machine learning system with certain kernels of knowledge about intuitive physics built in… akin to what an infant might be…
