If your data set is too small, they memorize. If you train them well on a large dataset, they learn to generalize.
they only generalise with big datasets, that is the rule
That's what I said.
Do Machine Learning Models Memorize or Generalize?
141–150 of 217 posts
Re: Do Machine Learning Models Memorize or Generalize?
#142Earlier quoted context omitted.
> I just don't think enough attention has been paid to the data, and too much the model. I wholly agree. Everyone is blinded by models - GPT4 this, LLaMA2 that - but the real source of the smarts is in the dataset. Why would any model, no matter how its architecture is tweaked, learn about the same ability from the same data? Why would humans be all able to learn the same skills when every brain is quite different. I…
> It was the data, not the model It's both . It's clearly impossible to learn how to translate Linear A into modern English using only content written in pure Japanese that never references either. Yet also, none of the algorithms before Transformers were able to first ingest the web, then answer a random natural language question in any domain — closest was Google etc. matching on indexed keywords. > how are AIs goi…
> Yet also, none of the algorithms before Transformers were able to first ingest the web, then answer a random natural language question in any domain — closest was Google etc. matching on indexed keywords.
Wrong, recurrent models were able to do this, just not as well.
Re: Do Machine Learning Models Memorize or Generalize?
#143Earlier quoted context omitted.
> I just don't think enough attention has been paid to the data, and too much the model. I wholly agree. Everyone is blinded by models - GPT4 this, LLaMA2 that - but the real source of the smarts is in the dataset. Why would any model, no matter how its architecture is tweaked, learn about the same ability from the same data? Why would humans be all able to learn the same skills when every brain is quite different. I…
This is definitely current models' biggest issue. You're training a model against millions of books worth of data (which would take a human tens of thousands of lifetimes) to achieve a superficial level of conversational ability to match a human, which can consume at most 3 novels a day without compromising comprehension. Current models are terribly inefficient when it comes to learning from data.
You have to count the training process from the origin of the human brain imo, not from the birth of any individual human.
Neural nets look much more competitive by that standard.
Re: Do Machine Learning Models Memorize or Generalize?
#144Earlier quoted context omitted.
The inspiration for weight decay was to reduce the capacity to memorize of the model until it perfectly fits the complexity of the task, not more not less. A model more complex than the task is over-fitting, the other one is under-fitting. Got to balance them out. But the best cure for over-fitting is to make the dataset larger and ensure data diversity. LLMs have datasets so large they usually train one epoch.
And there have been a lot of approaches to do this, my favorite one being the idea that maybe if we just randomly zap out some of the neurons while we train the rest, that forcing it to acquire that redundancy might privilege structured representations over memorization. Just always seemed like some fraternity prank, “if you REALLY know the tenets of Delta Mu Beta you can recite them when drunk after we spin you arou…
Re: Do Machine Learning Models Memorize or Generalize?
#145Earlier quoted context omitted.
Afaik weight decay is inspired from L2 regularisation which goes back to linear regression where L2 regularisation is equivalent to having gaussian prior on the weights with zero mean. Note that L1 regularisation produces much more sparsity but it doesn't perform as well.
This. Weight decay is just a method of dropping most weights to zero which is a standard technique used by statisticians for regularization purposes for decades. As far as I understand, it goes back at least to Tikhorov from 1970 and was mostly called ridge regression in the regression context. Normal ordinary least squares attempts to minimize the L2 norm of the squared residuals. When a system is overdetermined, ad…
this comment is so off base, first off no l2 des not encourage near 0 weights, second off they are not relearning, everyone already knew what l1/l2 penalties are
Re: Do Machine Learning Models Memorize or Generalize?
#146Grr, 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 literally do not see the difference between the two uses that you are trying to make
Re: Do Machine Learning Models Memorize or Generalize?
#147Sometimes 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…
Maxwell’s demon to entropy
Re: Do Machine Learning Models Memorize or Generalize?
#148Earlier quoted context omitted.
Can "distill knowledge" be made precise ?
imo, it amounts to revisiting concepts once more general principles are found — and needed. For instance, you learn the alphabet, and it's hard. the order is tricky. the sounds are tricky, etc. but eventually, it get distilled to a pattern. But you still have to start from A to remember what letter 6 is, until you encounter that problem many times, and then the brain creates a 6=F mapping. I think of it in economic t…
It’s almost like a tuning fork. When the mapping becomes 6=F the two separate tuning forms are now sympathetic to a frequency.
Re: Do Machine Learning Models Memorize or Generalize?
#149Sometimes 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…
For more information and the related math behind associative memories, please see Hopfield Neural Networks. While the upper bound is technically "infinity", there is a tradeoff between the amount of concepts stored and the fundamental amount of information storable per concept, similar to how other tradeoff principles like the uncertainty principle, etc work.
Thank you
Re: Do Machine Learning Models Memorize or Generalize?
#150Earlier quoted context omitted.
Maybe humans are also failing a lot in out of distribution settings. It might be inherent.
We have names for that. :D. Stereotypes being a large one. Racism being motivated interpretation on the same ideas. Right?
Yes, although there are less political examples. PTSD, the difficulty of learning higher dimensional mathematics in a way you can genuinely understand, substance abuse, mass killings.