AI 与机器学习incompleteideas.net编辑精选
苦涩的教训
The Bitter Lesson
2019 — 2022，它一次次回到首页
黑点是上首页（≥ 50 分）的那次投稿，空心点是没冲上去的投稿，点越大分数越高。
导读
这篇经典短文《The Bitter Lesson》回顾 AI 研究史，指出依赖人类领域知识的精巧方法，长期看往往会被能随算力增长而扩展的通用方法（尤其是搜索和学习）超越。作者由此主张，研究者应接受这一“苦涩教训”，少把人类先验塞进系统，更多押注可扩展的通用方法。
为什么经久不衰：它把“算力与通用方法终将压倒人类巧思”的争论浓缩成一篇常被引用也常被反驳的短文，今天讨论 scaling、先验和通用方法时仍绕不开。
HN 评论精选
算力必要但不充分，视觉突破还依赖训练技巧、数据集和架构创新。
这篇文章把一切归因于算力，过于简化。Deep Blue 用暴力搜索下棋当然符合，但其他例子呢？以计算机视觉为例，2012 年 AlexNet 在 ImageNet 上大胜，模型里的基本组件上世纪 80 年代末就已知，但此前我们不知道如何训练深网络（初始化很重要），也没有足够大的数据集；之后模型又提升一个数量级，主要靠架构改进——巧思加大量试错。所以算力必要但不充分，我不认为图像识别像国际象棋那样被“暴力破解”了。
sweezyjeezy查看英文原文
This post oversimplifies the story by putting all the emphasis on compute power. Deep Blue using brute force to solve chess obviously fits this pattern, but the others? Let's take computer vision. Alex Krizhevsky et al destroyed the ImageNet competition with a neural network in 2012, kicking off the current AI hype cycle. Essentially everything in their model had been known about since the late 80s. But we also didn't know how to train deep networks much before this (it turned out how you initialise the neural network was important), and we also didn't have a big enough dataset to train such a deep model on until ImageNet. Since then, we have built models that perform another order of magnitude better than the 2012 model, mainly because of improvements to the architectures (a combination of ingenuity and a lot of trial and error). So compute is necessary, but it isn't enough, I don't buy that we've 'brute forced' image recognition in the same way as chess.
Deep Blue 并非纯暴力，专家知识深植设计；真正该问的是人类为何无需搜索也下得好。
“大规模深度搜索”其实从开局棋谱和多位大师的专家知识出发，用的是专为两人确定性游戏设计的 minimax+alpha-beta，以及手工评估函数（参数由自对弈填充）。盲搜索不可能自己发明 minimax 或评估函数；人类关于棋局关键因素的专长从一开始就嵌入了 Deep Blue。搜索当然让它获胜，但更有用的教训不是“大机器算得多”，而是为什么人类不靠搜索也能下得这么好——这一点我们还没学会。
YeGoblynQueenne查看英文原文
>> In computer chess, the methods that defeated the world champion, Kasparov, in 1997, were based on massive, deep search. "Massive, deep search" that started from a book of opening moves and the combined expert knowledge of several chess Grandmasters. And that was an instance of the minimax algorithm with alpha-beta cutoff, i.e. a search algorithm specifically designed for two-player, deterministic games like chess. And with a hand-crafted evaluation function, whose parameters were filled-in by self-play. But still, an evaluation function; because the minimax algorithm requires one and blind search alone did not, could not, come up with minimax, or with the concept of an evaluation function in a million years. Essentially, human expertise about what matters in the game was baked-in to Deep Blue's design from the very beginning and permeated every aspect of its design. Of course, ultimately, search was what allowed Deep Blue to beat Kasparov (3½–2½; Kasparov won two games and drew another). That, in the sense that the alpha-beta minimax algorithm itself is a search algorithm and it goes without saying that a longer, deeper, better search will inevitably eventually outperform whatever a human player is doing, which clearly is not search. But, rather than an irrelevant "bitter" lesson about how big machines can perfom more computations than a human, a really useful lesson -and one that we haven't yet learned, as a field- is why humans can do so well without search. It is clear to anyone who has played any board game that humans can't search ahead more than a scant few ply, even for the simplest games. And yet, it took 30 years (counting from the Dartmouth workshop) for a computer chess player to beat an expert human player. And almost 60 to beat one in Go. No, no. The biggest question in the field is not one that is answered by "a deeper search". The biggest question is "how can we do that without a search"? Also see Rodney Brook's "better lesson" [2] addressing the other successes of big search discussed in the article. _____________ [1] https://en.wikipedia.org/wiki/Deep_Blue_(chess_computer)#Design [2] https://rodneybrooks.com/a-better-lesson/
从发育生物学看，搜索、学习和大量生成-选择也是大脑发育的核心机制。
我对 AI 几乎一无所知，但觉得这是很好的总结。作为曾经的发育生物学家，这两点让我印象深刻：一是通用方法的力量——能随算力增长而扩展的方法，尤其是搜索和学习；二是心智内容极其复杂，我们不应再找简单方式去理解空间、物体、多智能体或对称性等。据我所知，大脑发育中“搜索和学习”也是关键机制，再加上大量过度生成与选择，基本上就是学习。也许这是生物学的主要启示。
mirimir查看英文原文
I know ~nothing about AI. But to me, this seems a great summary. And as a one-time developmental biologist, I'm struck by these observations: > One thing that should be learned from the bitter lesson is the great power of general purpose methods, of methods that continue to scale with increased computation even as the available computation becomes very great. The two methods that seem to scale arbitrarily in this way are search and learning. > The second general point to be learned from the bitter lesson is that the actual contents of minds are tremendously, irredeemably complex; we should stop trying to find simple ways to think about the contents of minds, such as simple ways to think about space, objects, multiple agents, or symmetries. From what I know about brain development, "search and learning" are key mechanisms. Plus massive overproduction and selection, which is basically learning. Maybe that's the main takeaway from biology.
推荐 Rod Brooks 的回应文《A Better Lesson》，作为对本文的反驳或补充。
可能也值得一看 Rod Brooks 的回应《A Better Lesson》(2019)：https://rodneybrooks.com/a-better-lesson/
kdoherty查看英文原文
Potentially also of interest is Rod Brooks' response "A Better Lesson" (2019): https://rodneybrooks.com/a-better-lesson/
历次讨论
同类还值得读
如何写一个拼写纠正器
How to Write a Spelling Corrector
Peter Norvig 用一个几十行的 Python 程序演示如何做拼写纠正：先用编辑距离（删除、插入、替换、换位）生成所有可能的候选词，再用从大量文本中统计出的词频概率，选出…
AI 与机器学习上首页 10 次 · 2007–2022norvig.com编辑精选面向黑客的概率编程与贝叶斯方法
Probabilistic Programming and Bayesian Methods for Hackers (2013)
《黑客的贝叶斯方法与概率编程》是一本开源的贝叶斯统计入门书，以 Python/PyMC 代码和交互式 Jupyter Notebook 为主线，强调“先实践、后数学”的学习路径，…
AI 与机器学习上首页 5 次 · 2013–2018camdavidsonpilon.github.io编辑精选神经网络黑客指南
Hacker's Guide to Neural Networks
Andrej Karpathy 写的神经网络入门教程，面向程序员，从最简单的表达式求导讲起，逐步推导出反向传播和梯度下降，最后引出神经网络。
AI 与机器学习上首页 4 次 · 2014–2019karpathy.github.io编辑精选神经网络能逼近任意函数的可视化证明
A visual proof that neural nets can approximate any function
这一章来自 Michael Nielsen 的在线书《Neural Networks and Deep Learning》，用 sigmoid 单元叠加成局部隆起/平滑阶跃的图示…
AI 与机器学习上首页 4 次 · 2014–2022neuralnetworksanddeeplearning.com编辑精选论乔姆斯基与统计学习的两种文化
On Chomsky and the Two Cultures of Statistical Learning
Norvig 回应 Chomsky 对统计语言模型批评的文章，围绕“统计学习能否解释语言”展开，比较生成与解释、少参数模型与 Shannon 式高参数统计模型。
AI 与机器学习上首页 4 次 · 2011–2025norvig.com编辑精选