AlphaGo, every mention

mentionsepisodesper episode tap a year for its mentions

Verbatim, from the transcripts: the passages where AlphaGo comes up

loading…

▶ 4:14 Dan Roberts And around that time, I'm pretty old now for, at least for this field, so that was about 20 16, uh, was when the DQN Atari paper from DeepMind happened in 2015, and then AlphaGo was in 2016, and I got very excited about these, um, about…

▶ 18:52 Eiso Kant Think here a little bit of what we see with AlphaGo and, you know, these kinds of systems where, where there's an exploration step.

▶ 4:56 Mathew Lodge So if you think about things like Google Alpha Go is based on reinforcement learning where you're searching for the best Go move. 3 times in the scene

▶ 5:56 Sarah Catanzaro Um, I think what we learned back in, uh, 2017, 20 18, when there was a lot of hype around reinforcement learning, GANs, uh, things like AlphaGo, uh, things like Alexa, was that

▶ 15:47 Pedro Domingos Like, you know, AlphaGo is a great example, right?
▶ 19:44 Pedro Domingos You know, like, AlphaGo spent, played millions of games. 2 times in the scene

▶ 5:07 Gary Marcus Deep learning has played a role in the great performance in games like AlphaGo and, and, um, so forth.
▶ 17:16 Gary Marcus It's totally different from trying things a million times, which is what, say, AlphaGo does when plays Go.
▶ 21:50 Gary Marcus I mean, you can either use the kind of brute force that, um, you know, Deep Blue used and just searched through a lot of positions, or there's a more nuanced version of, of brute force in AlphaGo, um, which combines Monte Carlo Tree… 2 times in the scene
▶ 35:23 Gary Marcus So like, DeepMind made a big deal of AlphaGo as a deep learning system, but it has this Monte Carlo Tree Search stuff that precedes deep learning that comes from classical AI. 2 times in the scene

Turn any episode into a week of clips.