EPISODE · Apr 9, 2026 · 41 MIN
vol.67 AI特辑#4：AI曾经走过的技术路线
from 逃课沙龙
vol.67 AI特辑#4：AI曾经走过的技术路线本期逃课沙龙，我们尽可能以简单通俗的方式向大家介绍AI训练中曾经比较主流的几个模型架构，包括残差网络，卷积神经网络(CNN)，变分编码器（VAE），扩散模型等等。除此之外，我们也聊到了过去比较火热的AlphaGo 和Alpha Zero。 那更像人脑的AI就会表现得更好吗？这些技术路线有多大程度上从人脑中获得灵感，又能如何反哺神经科学的发展呢？这些技术路线又将带领我们去往什么方向？音乐Snarky Puppy feat. Magda Giannikou - Amour T'es Là (开场音乐)主播 内森、吸鸭
Embed this episode
NOW PLAYING
vol.67 AI特辑#4：AI曾经走过的技术路线
0:00
41:09
1×
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
Frequently Asked Questions
How long is this episode of 逃课沙龙?
This episode is 41 minutes long.
When was this 逃课沙龙 episode published?
This episode was published on April 9, 2026.
Can I download this 逃课沙龙 episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!