神经科学与心理学2020arxiv.org编辑精选
过拟合的大脑：梦是为辅助泛化而演化出来的
The Overfitted Brain: Dreams evolved to assist generalization
入门 · 约 30 分钟读完前置知识：过拟合与泛化概念、睡眠与做梦的基础知识、演化生物学基础
导读
这篇论文提出“过拟合大脑假说”：大脑在日常学习中会像深度神经网络一样出现过拟合，而每晚的梦（尤其是做梦睡眠）是演化出来对抗过拟合的机制，作用类似训练 DNN 时注入噪声，帮助大脑更好地泛化。文章还以 2020 年疫情期间人们报告梦境更生动、更频繁的现象作为讨论背景。
HN 关注点：把深度学习的过拟合/正则化直接类比到大脑与梦的功能上，讨论焦点是这种跨领域类比是否有解释力、可证伪，以及作者对 DNN 训练的理解是否已过时。
HN 评论精选
这几条评论里：质疑 3 补充 1
质疑论文忽略“双下降”现象——过拟合可能是泛化的必经阶段，其对 DNN 的理解已经过时。
这篇论文主张 DNN 学习时会过拟合，常用噪声注入解决，而大脑面临类似挑战、梦就是演化出来对抗过拟合的。但实际上有有力证据表明，过拟合是 DNN 达到 SOTA 性能的必要步骤：许多最先进模型在训练集上达到约 100% 准确率后继续训练，越过“插值阈值”后反而能更好地泛化到未见数据，这就是“双下降”（double descent）现象（参见 OpenAI 的 deep double descent 博客及 arXiv 1912.02292、1903.08560）。作者完全没提双下降和对过拟合的需求，似乎对此毫不知情。
cs702查看英文原文
> ... all DNNs face the issue of overfitting as they learn, which is when performance on one data set increases but the network's performance fails to generalize (often measured by the divergence of performance on training vs testing data sets). This ubiquitous problem in DNNs is often solved by experimenters via "noise injections" in the form of noisy or corrupted inputs. The goal of this paper is to argue that the brain faces a similar challenge of overfitting, and that nightly dreams evolved to combat the brain's overfitting during its daily learning. Actually, there's compelling evidence that overfitting is a necessary step for achieving state-of-the-art performance with DNNs! Many state-of-the-art deep learning models today are trained until they achieve ~100% accuracy on the training data, and then we continue to train them because once they go past this "interpolation threshold" they continue learning to generalize better to unseen data. This is known as the "double descent" phenomenon. See, for example: https://openai.com/blog/deep-double-descent/ https://arxiv.org/abs/1912.02292 https://arxiv.org/abs/1903.08560 The author makes no mention of double descent and the need for overfitting. In fact, he seems completely unaware of it. -- EDIT: Also, see this comment https://news.ycombinator.com/item?id=23957501 elsewhere on this page.
补充类似观点 Matthew Walker 早已提出，论文并非首创，但提供了可定量讨论的框架。
Matthew Walker 在《Why We Sleep?》一书中提出过类似观点：做梦睡眠对建立联想至关重要，也就是泛化和消除过拟合。他谈到睡眠中的问题解决如何带来醒来时的“啊哈”时刻。也就是说，这篇论文的想法其实已经“存在”了，与摘要的说法相反。不过能有一个可定量讨论的框架还是令人兴奋的。
sgdpk查看英文原文
In the book "Why we sleep?", Matthew Walker suggests something similar. That dream sleep is fundamental in making associations. In this case, generalizing and getting rid of overfitting. He talks a bit about problem solving when sleeping and how this leads to "a-ha" moments when waking up. This means that the idea in this paper is already "out there", contrary to what the abstract states. But it's exciting to have a framework to talk about it quantitatively.
质疑用深度学习类比大脑是不可证伪的牵强附会，属于“DL 中心主义”的过度延伸。
我预感会被踩，但总得找地方吐槽。这种荒谬的狂妄该有个名字：不可证伪的“非洞见”，来自那些试图把任意的深度学习算法套用到大脑上的人——而大脑显然一个都没在用。DL 中心主义？我们连大脑怎么做几乎任何事都还不知道，你却以为能用时髦的 AI 话题解释梦这样复杂神秘的东西？这让我想起 Matt Walker 那本糟糕的睡眠书：几乎当下所有神经科学研究都试图解释某种行为模式或体验的“为什么”，却从不真正给出解释，只说“这个区域在 fMRI 里亮起来了”，好像这就回答了问题。就像你问“心脏为什么泵血”，心脏科医生回答“心脏对运动很重要，心脏健康的人活得更久，接上电极还能看到与脉搏呼吸相关的有趣模式”。正因为对如此难理解的东西你根本无法证伪，这类过度延伸的论文才得以发表。
TaupeRanger查看英文原文
I'm foreseeing impending downvotes but I have to rant somewhere. There should be a name for this kind of ridiculous hubris. Unfalsifiable non-insights by people trying to apply arbitrary deep learning algorithms to a brain which is definitely not using any of them. DLcentrism? We don't even know how the brain does almost anything and you think you can use trendy AI topics to explain something as complex and mysterious as dreams? This reminds me of Matt Walker's terrible book on sleep, which, as with almost all neuroscience research recently, tries to explain "why" we have some behavioral pattern or experience, but literally never offers an explanation at all, opting to say "this region lights up in an fMRI machine", as if that answers anything at all. It's like if you asked "why does the heart pump blood?" and a cardiologist answered, "well, the heart is very important for exercise, and people with healthy hearts live longer, and when we attach electrodes to it we see these interesting patterns associated with pulse and breathing...". That's Matt Walker's book applied to the brain. This allows "neuroscience" to get away these ridiculously overextended papers, because you can't disprove anything about something so hard to understand in the first place.
质疑论文对普通读者友好，但错别字多到连核心概念都拼错，开头有高中生作文式的空话感。
摘要确实引人入胜，我正在读全文，到目前为止对门外汉来说大部分很容易理解。不过大量拼写错误让我有点出戏。有趣的是他们甚至把核心概念拼错了——“Overfitted Brian Hypothesis”（Brian 应为 Brain）。我得说，开头那段让我想起无脑高中作文里的空话：“在 2020 年 Covid-19 疫情期间，许多隔离中的人报告说梦境变得更生动、更频繁（Weaver, 2020），甚至让 #pandemicdreams 上了 Twitter 热搜。然而人们对梦知之甚少，对于这种普遍的梦境变化背后的原因，只能给出推测性的答案。”
jere查看英文原文
The abstract is indeed fascinating and I'm reading through the full text, which is so far mostly easy to understand for a layman. The high number of typos throws me a bit though. Amusingly they even misspell their central idea "Overfitted Brian Hypothesis" and I gotta say that the opening reminds me a bit of fluff you see in mindless high school essays. > During the Covid-19 pandemic of 2020, many of those in isolation reported an increase in the vividness and frequency of their dreams (Weaver, 2020), even leading #pandemicdreams to trend on Twitter. Yet dreaming is so little understood there can be only speculative answers to the why behind this widespread change in dream be- havior.
相关资源
从这篇论文所有 HN 讨论帖的全部评论里整理出来的链接。
历次讨论
- 2020Hacker News 讨论帖195 分 · 71 评
同领域还值得读
神经科学家能理解微处理器吗？（2017）
Could a Neuroscientist Understand a Microprocessor? (2017)
提出一个思想实验：把神经科学常用的分析方法（损伤实验、电生理、功能定位等）应用到一个我们完全了解其原理的工程系统——6502 微处理器（运行游戏）上，检验这些方法能否真正“理解”…
神经科学与心理学2017 · 411 分 · 135 评进阶 · 约 60 分钟编辑精选大脑衰老呈现非线性转变，提示中年“关键窗口”
Brain aging shows nonlinear transitions, suggesting a midlife "critical window"
这篇 PNAS 论文研究大脑衰老的非线性变化，发现大脑老化并非匀速进行，而是在中年（约 40-60 岁）存在一个关键的"临界窗口期"，此时干预可能有效。
神经科学与心理学2025 · 295 分 · 159 评进阶 · 约 75 分钟编辑精选社交网络中大规模情绪传染的证据（2014）
Evidence of massive-scale emotional contagion through social networks (2014)
这篇 2014 年发表于 PNAS 的论文研究了 Facebook 上约 70 万用户的信息流中，减少正面或负面内容是否会传染性地影响用户自己发布内容的情绪。
神经科学与心理学2020 · 285 分 · 72 评入门 · 约 45 分钟编辑精选裸盖菇素使人类大脑去同步化
Psilocybin desynchronizes the human brain
这篇 Nature 研究用个体化的 fMRI 精密成像追踪受试者服用裸盖菇素（psilocybin）前后的脑功能连接变化，发现药物会造成大范围的脑网络「去同步化」，尤其是默认模式…
神经科学与心理学2024 · 273 分 · 259 评进阶 · 约 60 分钟编辑精选对智力的赞扬会削弱儿童的动机与表现（1998）
Praise for Intelligence Can Undermine Children's Motivation (1998)
这篇 1998 年的经典论文（Dweck 等人）通过实验研究表扬方式对儿童动机的影响：夸孩子“聪明”（表扬智力）会让他们回避挑战、害怕失败，而表扬努力则更能培养坚持性。
神经科学与心理学2016 · 253 分 · 155 评入门 · 约 45 分钟编辑精选