Live data from Hacker News

The overfitted brain: Dreams evolved to assist generalization

cell.com

21–30 of 83 posts

Re: The overfitted brain: Dreams evolved to assist generalization

#21
> Sleep loss, specifically dream loss, leads to an overfitted brain that can still memorize and learn but fails to generalize appropriately

Curious where this claim came from. Obviously a lack of sleep will degrade your day-to-day performance, but I almost never have dreams.

Re: The overfitted brain: Dreams evolved to assist generalization

#22

> Sleep loss, specifically dream loss, leads to an overfitted brain that can still memorize and learn but fails to generalize appropriately Curious where this claim came from. Obviously a lack of sleep will degrade your day-to-day performance, but I almost never have dreams.

Or you just don’t remember them.

Re: The overfitted brain: Dreams evolved to assist generalization

#23

> Sleep loss, specifically dream loss, leads to an overfitted brain that can still memorize and learn but fails to generalize appropriately Curious where this claim came from. Obviously a lack of sleep will degrade your day-to-day performance, but I almost never have dreams.

From what I recall, everybody dreams an approximately equal amount of time every night, the only major difference is how much of it is forgotten when you wake up.

I wish I recalled (..or saved) the paper, but waking up releases a chemical in the brain that makes you actively and quickly forget what you just dreamed about.

Re: The overfitted brain: Dreams evolved to assist generalization

#25
post #4

> 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 s…

And if the brain is overfitted, how can it generate out-of-distribution samples? Seems like wildly cyclical reasoning.

Re: The overfitted brain: Dreams evolved to assist generalization

#26
post #25
post #4

> 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 s…

And if the brain is overfitted, how can it generate out-of-distribution samples? Seems like wildly cyclical reasoning.

How can computers calculate more accurately than the human brain but also have PRNGs or even true hardware RNGs?

Re: The overfitted brain: Dreams evolved to assist generalization

#27
post #25
post #4

> 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 s…

And if the brain is overfitted, how can it generate out-of-distribution samples? Seems like wildly cyclical reasoning.

The brain is a lot of different components working together. Perhaps the bits which do statistical learning are functionally distinguishable from the bits which generate permutations on the data.

(This is in fact how modern neural network training often works: start with a set of 50,000 images, run them through a bunch of permutations — translation, rotation, lighting changes, etc. — and produce a training set of 1 million images which yield better generalization when trained against.)

Re: The overfitted brain: Dreams evolved to assist generalization

#29
A theory of dreams should imo mention a few things:

* Lucid dreaming. In particular does lucid dreaming prevent the generalization benefits?

* Sensory deprivation hallucinations. It would seem this is connected to dreams, but is it?

* Tetris effect. It seems that seeing a lot of a given pattern primes the brain the brain to look for it everywhere.

Post reply on HN