Yann LeCun:能量基模型是理解各类深度学习的统一框架
LeCun 把分类、自监督、扩散模型、JEPA 全塞进能量基模型一个框架讲,还给了免费课程链接、2006 年教程论文和 2019 年讲座。想搞懂 JEPA 到底是什么、和 diffusion 有啥关系的人直接看这套材料最省事。
Yann LeCun 在 X 上表示,他过去约 20 年在 NYU 的 Deep Learning 课程核心观点是:分类、回归、结构化预测、无监督与自监督学习都能放进 energy-based models 这一统一框架内理解。
他列举了该框架覆盖的方法,包括 clustering、auto-encoders、denoising AE、variational AE、Siamese nets、joint embedding、JEPA 以及 diffusion models,并指向 2021 年课程(atcold.github.io/NYU-DLSP21/)的第 3 和第 4 主题作为学习材料。
配套资源方面,@alfcnz 正基于该课程编写一本 EBM 教科书;LeCun 还提供了两个原始材料:2019 年在 IAS 关于用 EBM 理解自监督学习的讲座(youtu.be/m17B-cXcZFI)和 2006 年的 EBM 教程论文(yann.lecun.com/exdb/publis/pd…)。这套论述与 Meta 近年押注 JEPA 架构的方向一致,对想系统理解自监督学习原理的开发者是完整的免费资料链。
That's the essence of my Deep Learning course at NYU for the past 20 years or so. Everything can be understood within the unified framework of energy-based models, including classification, regression, structured prediction, unsupervised and self-supervised learning (clustering, auto-encoders, denoising AE, variational AE, Siamese nets, joint embedding, JEPA, diffusion models,...). Look at themes 3 and 4 from our 2021 course: atcold.github.io/NYU-DLSP21/ @alfcnz has been working on an EBM textbook derived from my course. Here is a lecture I gave at IAS in 2019 about understanding SSL with EBM youtu.be/m17B-cXcZFI?is… There is also my 2006 EBM tutorial paper: yann.lecun.com/exdb/publis/pd…📊 29 ⚡
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Yann LeCun, JEPA, self-supervised learning, NYU.
Source attribution: curated from Yann LeCun (@ylecun).