Max Welling
① 他说过的话
10 条
相对这些量子力学近似，有三到四个数量级的加速，效率更高。
指向原始笔记的链接
Three-order to four-order magnitude acceleration, more efficiency relative to these quantum mechanical approximations.
—— Max Welling · [04:57]
所以我们现在能做的，基本上就是为一个非常具体的任务提出一个全新的分子，然后在实验室里制造它，再把它用于那个特定任务。
指向原始笔记的链接
And so what we can do is we can now basically come up with an entirely new molecule for a very specific task and then make it in the lab and then use that for that particular task.
—— Max Welling · [13:16]
我们的一些科学家说过：我们现在几天就能做完以前一个博士周期才能做完的事，但这更多是在数字领域。
指向原始笔记的链接
So some of our scientists, they have said things like, we can do now in a few days what took a PhD before, but that’s more in the digital domain.
—— Max Welling · [22:04]
现代生成式 AI，包括概率模型、扩散模型和许多其他东西，它们的数学结果等同于描述现代非平衡统计力学或热力学的数学。
指向原始笔记的链接
Modern generative AI, including probabilistic models, including diffusion models, and many other things, their mathematics turns out to be equivalent to the mathematics that describes modern non-equilibrium statistical mechanics or thermodynamics.
—— Max Welling · [35:06]
物理学的核心是信息论。
指向原始笔记的链接
At the core of physics is information theory.
—— Max Welling · [36:06]
扩散模型其实就是一个把结构取来并毁掉的过程，这通常是世界上发生的事，熵随之上升；然后我们尝试在时间上逆转它——从噪声出发创造结构，这就是我们的生成模型。
指向原始笔记的链接
So diffusion models really are a process by which you take structure and you destroy it, which is typically what happens in the world. The entropy goes up. And then we try to reverse that backward in time, which is to start with noise and create structure, which is our generative models.
—— Max Welling · [41:02]
热和功、熵产生这些概念，我们谈论机器学习模型时并不使用，但我认为它们为思考正在发生什么、以及如何改进模型，提供了一个非常新颖且有趣的视角。
指向原始笔记的链接
Concepts like heat and work and entropy, production, these things we don’t use when we talk about machine learning models, but I think they give you a very new and interesting perspective on how to think about what’s going on and how to also improve them.
—— Max Welling · [45:03]
所以你真正想要的是处在中间某处——不太稳定也不太不稳定——这叫混沌边缘。人们已经发现，事实上表现最好的神经网络就在这个混沌边缘上运行。
指向原始笔记的链接
So what you really want is sitting somewhere in the middle, somewhere that’s not too stable and not too unstable, and that’s called edge of chaos. And people have found that, in fact, neural networks that perform best operate at this edge of chaos.
—— Max Welling · [52:34]
我们还发现，如果在神经网络中加入这些波，你会非常自然地运行在混沌边缘，而不必微调系统去凑到那里。
指向原始笔记的链接
And we found that if you include these waves in your neural network, you very naturally operate in this regime edge of chaos, and you don’t have to fine-tune the system to be there.
—— Max Welling · [52:58]
所以在这里，我们把物理的一个深层结果用作神经网络的设计原理。
指向原始笔记的链接
And so here we use something, a deep result from physics as a design principle for neural networks.
—— Max Welling · [56:53]
② 出现在这些集
1 集
③ 他谈到的
点进去有真内容 —— 本页主要出口
Sam Charrington · cusp.ai · 智能体 · 等变性 · 扩散模型 · 自发对称性破缺 · 波 · 机器学习力场 · 分子动力学 · 金属有机框架