Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Do Machine Learning Models Memorize or Generalize?

pair.withgoogle.com

Post reply on HN
Print view View original

111–120 of 217 posts

Re: Do Machine Learning Models Memorize or Generalize?

#111

Post by __loam »

downboots wrote: post #56
ComputerGuru wrote: post #45

Earlier quoted context omitted.

That’s not exactly true, there doesn’t seem to be an upper bound (that we can reach) on storage capacity in the brain [0]. Instead, the brain actually works to actively distill knowledge that doesn’t need to be memorized verbatim into its essential components in order to achieve exactly this “generalized intuition and understanding” to avoid overfitting. [0]: https://www.scientificamerican.com/article/new-estimate-bo…

Can "distill knowledge" be made precise ?

Unless you know something the neuroscientists don't, it cannot.

Re: Do Machine Learning Models Memorize or Generalize?

#112

Post by __loam »

imtringued wrote: post #99
nonameiguess wrote: post #75

Earlier quoted context omitted.

I've thought about this a lot in the context of the desire people seem to have to try and achieve human immortality or at least indefinite lifespans. If SciAm is correct here and the upper bound is a quadrillion bytes, we may not be able to hit that given the bound on possible human experiences, but someone who lived long enough would eventually hit that. After a hundred million years or whatever the real number is o…

Longtermists argue that we will be harvesting hawking radiation from blackholes trillions of years after the heat death of the universe.

The last civilizations will be built around black holes.

Re: Do Machine Learning Models Memorize or Generalize?

#113

Post by hgsgm »

bufferoverflow wrote: post #79
mostertoaster wrote: post #37

Sometimes I think the reason human memory in some sense is so amazing, is what we lack in storage capacity that machines have, we makeup for in our ability to create patterns that compress the amount of information stored dramatically, and then it is like we compress those patterns together with other patterns and are able to extract things from it. Like it is an incredibly lossy compression, but it gets the job done…

There are rare people who remember everything https://youtu.be/hpTCZ-hO6iI

Is there scientific evidence of that or just claims?

Re: Do Machine Learning Models Memorize or Generalize?

#114

Post by 93po »

svachalek wrote: post #101
bufferoverflow wrote: post #79

Earlier quoted context omitted.

There are rare people who remember everything https://youtu.be/hpTCZ-hO6iI

It's pretty fascinating to me how "normal" Marilu Henner seems to be. I'm getting older and my memory is not what it was, but when I was younger it was pretty extraordinary. I did really well in school and college but over time I've realized it was mostly due to being able to remember most things pretty effortlessly, over being truly "smart" in a classic sense. But having so much of the past being so accessible is to…

As someone on the other end of the spectrum, I have an awful memory, and don't remember most of my life aside from really wide, sweeping generalizations and maybe a couple hundred very specific memories. My way of existence is also very sad, and it makes me feel like I've not really lived.

Re: Do Machine Learning Models Memorize or Generalize?

#116

Post by 93po »

gorjusborg wrote: post #22

Grr, the AI folks are ruining the term 'grok'. It means roughly 'to understand completely, fully'. To use the same term to describe generalization... just shows you didn't grok grokking.

I have heard grok used tremendously more frequently in the past year or two and I find it annoying because they're using it as a replacement for the word "understand" for reasons I don't "grok"

Re: Do Machine Learning Models Memorize or Generalize?

#117

Post by jimwhite42 »

I'm not sure if I'm remembering it right, but I think it was on a Raphaël Millière interview on Mindscape, where Raphaël said something along the lines of when there are many dimensions in a machine learning model, the distinction between interpolation and extrapolation is not clear like it is in our usual areas of reasoning. I can't work out if this could be something similar to what the article is talking about.

Re: Do Machine Learning Models Memorize or Generalize?

#118

Post by ShamelessC »

tbalsam wrote: post #109
erwald wrote: post #24

Earlier quoted context omitted.

"Grok" in AI doesn't quite describe generalization, it's more specific that that. It's more like "delayed and fairly sudden generalization" or something like that. There was some discussion of this in the comments of this post[1], which proposes calling the phenomenon "eventual recovery from overfitting" instead. [1] https://www.lesswrong.com/posts/GpSzShaaf8po4rcmA/qapr-5-gro...

Part of the issue here is posting a LessWrong post. There is some good in there, but much of that site is like a Flat Earth conspiracy theory for neural networks. Neural network training [edit: on a fixed point task, as is often the case {such as image->label}] is always (always) biphasic necessarily, so there is no "eventual recovery from overfitting". In my experience, it is just people newer to the field or just n…

> Part of the issue here is posting a LessWrong post. There is some good in there, but much of that site is like a Flat Earth conspiracy theory for neural networks.

Indeed! It’s very frustrating that so many people here are such staunch defenders of LessWrong. Some/much of the behavior there is honestly concerning.

Re: Do Machine Learning Models Memorize or Generalize?

#119

Post by joaogui1 »

tbalsam wrote: post #105
greenflag wrote: post #5

It seems the take home is weight decay induces sparsity which helps learn the "true" representation rather than an overfit one. It's interesting the human brain has a comparable mechanism prevalent in development [1]. I would love to know from someone in the field if this was the inspiration for weight decay (or presumably just the more equivalent nn pruning [2]). [1] https://en.wikipedia.org/wiki/Synaptic_pruning [2…

ML researcher here wanting to offer a clarification. L1 induces sparsity. Weight decay explicitly _does not_, as it is L2. This is a common misconception. Something a lot of people don't know is that weight decay works because when applied as regularization it causes the network to approach the MDL, which reduces regret during training. Pruning in the brain is somewhat related, but because the brain uses sparsity to…

That looks interesting, do you know what paper talks about the connection between MDL, regret, and weight decay?

Re: Do Machine Learning Models Memorize or Generalize?

#120

Post by mdp2021 »

krapp wrote: post #80
smolder wrote: post #73

Earlier quoted context omitted.

Language devolves just as it evolves. We (the grand we) regularly introduce ambiguity --words and meanings with no useful purpose, or that are worse than useless. I'm not really weighing in on the appropriateness of the use "grok" in this case. It's just a pet peeve of mine that people bring out "language evolves" as an excuse for why any arbitrary change is natural and therefore acceptable and we should go with the…

Language only evolves, "devolving" isn't a thing. All changes are arbitrary. Language is always messy, fluid and ambigious. You should go with the flow because being a prescriptivist about the way other people speak is obnoxious and pointless. And "literally" has been used to mean "figuratively" for as long as the word has existed[0]. [0] https://blogs.illinois.edu/view/25/96439

> devolving isn't a thing

Incompetent use is devolution.

Post reply on HN