TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

The overfitted brain: Dreams evolved to assist generalization

178 pointsby hheikinhabout 4 years ago

20 comments

htrpabout 4 years ago
&gt; Notably, the techniques that researchers employ to rescue overfitted artificial neural networks generally involve sampling from an out-of-distribution or randomized dataset. The overfitted brain hypothesis is that the brains of organisms similarly face the challenge of fitting too well to their daily distribution of stimuli, causing overfitting and poor generalization. By hallucinating out-of-distribution sensory stimulation every night, the brain is able to rescue the generalizability of its perceptual and cognitive abilities and increase task performance.<p>Bit of jump there from randomized&#x2F;out of sample data to dreams are for generalization.
评论 #27202797 未加载
评论 #27201403 未加载
评论 #27202141 未加载
maxrev17about 4 years ago
Read something recently theorizing dreams are to prevent the visual processing part of the brain from being repurposed when we sleep...
评论 #27203777 未加载
评论 #27204753 未加载
评论 #27204194 未加载
评论 #27200863 未加载
评论 #27203368 未加载
slfnflctdabout 4 years ago
All I know is my dog sometimes yips in his sleep, and it can be fairly loud-- I will forever wonder what he&#x27;s yipping at, or how that behavior could possibly be selected for. Brains are weird.
评论 #27200520 未加载
评论 #27200194 未加载
评论 #27203828 未加载
评论 #27202053 未加载
euskeabout 4 years ago
My pet theory is a bit similar to the article but in a more computer-architecture way. I tend to think that sleep is our brain performing &quot;GC&quot; our experiences, i.e. choosing what information to retain and what to discard. Since we don&#x27;t have a separate circuit to do that, we basically reuse the same one (processor and its &quot;bus&quot;) for a different purpose, by redirecting its output to &#x2F;dev&#x2F;null, and that&#x27;s a dream. This kinda explains why we don&#x27;t remember much of it because the result is meant to be discarded. There&#x27;s no scientific evidence to this but it&#x27;s quite fun to think this way.<p>edit: the GC theory also explains why we have a better memory after sleep!
pacman2about 4 years ago
Oh wow. Cell. Please also see previous dicussion: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=23956715" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=23956715</a><p>I vaguely remember an Indian Paper (or an author with an Indian name) that made the same claims and it got destroyed on HN. But my memory may fail me.
评论 #27200422 未加载
babelfishabout 4 years ago
&gt; Sleep loss, specifically dream loss, leads to an overfitted brain that can still memorize and learn but fails to generalize appropriately<p>Curious where this claim came from. Obviously a lack of sleep will degrade your day-to-day performance, but I almost never have dreams.
评论 #27201270 未加载
评论 #27201062 未加载
FailMoreabout 4 years ago
For an alternative theory see <a href="https:&#x2F;&#x2F;psyarxiv.com&#x2F;k6trz" rel="nofollow">https:&#x2F;&#x2F;psyarxiv.com&#x2F;k6trz</a>
Severianabout 4 years ago
This seems true to me. Correlation doesn&#x27;t imply causation, but I&#x27;ve had my fair share of bizarre dreams where two completely separate concepts try to wedge themselves together in interlocking dream logic. No examples to speak of directly, as even holding them together after awakening is almost impossible.
bpicheabout 4 years ago
Also here<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=23956715" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=23956715</a><p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=27166536" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=27166536</a><p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=23922449" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=23922449</a>
refactor_masterabout 4 years ago
It strikes me as rather unintuitive that the brain should be generating its own “out-of-distribution” data. It’s training itself on itself? Compare with an adversarial network, which can be composed of two entirely separate entities, whereas the biological brain is know to have a lot of “bleed-through”, e.g. our memories influence our perception and vice versa.
pfdietzabout 4 years ago
I looked and was gratified it cited Francis Crick and Graeme Mitchinson&#x27;s paper from 1983 that had a very similar idea.
im3w1labout 4 years ago
A theory of dreams should imo mention a few things:<p>* Lucid dreaming. In particular does lucid dreaming prevent the generalization benefits?<p>* Sensory deprivation hallucinations. It would seem this is connected to dreams, but is it?<p>* Tetris effect. It seems that seeing a lot of a given pattern primes the brain the brain to look for it everywhere.
dr_dshivabout 4 years ago
Seems like it isn&#x27;t the randomization (high entropy) but rather the excessively low entropy. Sleeping brains are colder and more predictable (due to massive synchronization). REM sleep might be described as when our cortex turns on and tries sensemaking all the intrinsic oscillations.
canjobearabout 4 years ago
These theories are fun, but has it been shown that dreaming is an essential part of the function of sleep? If you could suppress dreaming but maintain sleep, would organisms still get the same benefit? Maybe what is required is simply a period of inactivity, and dreams are the effect of white noise cascading through the brain during that period.
评论 #27203783 未加载
giantg2about 4 years ago
I have too many dreams. It actually sucks since you don&#x27;t get great sleep.
评论 #27199253 未加载
评论 #27202773 未加载
t-writescodeabout 4 years ago
I find it fascinating how a strong atheistic perspective and premise still tries to ascribe meaning to things.<p>“Evolved to assist” and also most of the comments here that aren’t discussion of noticing animals dreaming.
评论 #27203571 未加载
prionassemblyabout 4 years ago
Ctrl-F &quot;mania&quot; says something. But on the level of barroom talk this sounds like a plausible explanation of the prodromal effects of sleep derivation.
xpuenteabout 4 years ago
DNN is a nice hammer, but brain is not a nail. Hopefully this hype will disappear soon.
quusabout 4 years ago
They talked about this on an episode of Very Bad Wizards
o_pabout 4 years ago
Or sleep is needed to clean the toxins in the brain and dreams are just a funny consequence of disconnecting you from the world
评论 #27201786 未加载