Machine Unlearning Challenge
ai.googleblog.com
Machine Unlearning Challenge
1–10 of 33 posts
Re: Machine Unlearning Challenge
#2While this post seems aimed more at compliance or sensitive data issues, “unlearning” aka forgetting itself may be essential for better or more human like AI agents. You are as much defined by what you have forgotten as what you have learned.
Re: Machine Unlearning Challenge
#3While this post seems aimed more at compliance or sensitive data issues, “unlearning” aka forgetting itself may be essential for better or more human like AI agents. You are as much defined by what you have forgotten as what you have learned.
I've heard than some mental illness (maybe schizophrenia) is theorized to be in part due to an inability to forget things. Certainly normal human existence involves preferential remembering and forgetting. For example not dwelling on pain or failure etc.
Gradient descent obviously has none of that, it has not feelings or goals, and so there would be no preferential remembering or forgetting other than to do better next word prediction or rlhf or whatever. So it would be interesting to think about what a model should remember or forget in order to align it with our goals (because it doesn't have any of it's own).
Also, don't volunteer for Google. They have lots of money, they can pay for this stuff and if you know how to do it you have lots of options.
Re: Machine Unlearning Challenge
#4An interesting idea. My first thought was to say “just use a differentially private learning algorithm,” but DP requires a notion of closeness, and that’s not trivial for, e.g., image data. Images close in an abstract sense, like Euclidean distance, may not be close in a task-relevant sense. You may not know what a good, task-relevant metric for employing DP without performing some kind of learning in the first place.
Re: Machine Unlearning Challenge
#5While this post seems aimed more at compliance or sensitive data issues, “unlearning” aka forgetting itself may be essential for better or more human like AI agents. You are as much defined by what you have forgotten as what you have learned.
it is certainly better for all AI agents, not just human like systems, because it is almost the definition of intelligence. Forgetting the irrelevant stuff and having a system that does as much as possible with as little information as possible is what learning is, compression in other terms.
Re: Machine Unlearning Challenge
#6Who knows… unlearning might turn out be good as a “sleep” phase while learning too. Sort of a regularisation. Could be done after each epoch.
Re: Machine Unlearning Challenge
#7This is an interesting concept. Is there something like an MNIST for this, to make it more concrete?
Re: Machine Unlearning Challenge
#8Joel: "Is there any risk of brain damage?"
Dr. Mierzwiak: "Well, technically speaking, the operation is brain damage, but it's on a par with a night of heavy drinking. Nothing you'll miss."
- Eternal Sunshine of the Spotless Mind (2004)
Re: Machine Unlearning Challenge
#9While this post seems aimed more at compliance or sensitive data issues, “unlearning” aka forgetting itself may be essential for better or more human like AI agents. You are as much defined by what you have forgotten as what you have learned.
I've heard than some mental illness (maybe schizophrenia) is theorized to be in part due to an inability to forget things. Certainly normal human existence involves preferential remembering and forgetting. For example not dwelling on pain or failure etc. Gradient descent obviously has none of that, it has not feelings or goals, and so there would be no preferential remembering or forgetting other than to do better ne…
Yeah, the prize for doing the best on this challenge should be a piece of the company.
Re: Machine Unlearning Challenge
#10While this post seems aimed more at compliance or sensitive data issues, “unlearning” aka forgetting itself may be essential for better or more human like AI agents. You are as much defined by what you have forgotten as what you have learned.
I've heard than some mental illness (maybe schizophrenia) is theorized to be in part due to an inability to forget things. Certainly normal human existence involves preferential remembering and forgetting. For example not dwelling on pain or failure etc. Gradient descent obviously has none of that, it has not feelings or goals, and so there would be no preferential remembering or forgetting other than to do better ne…
> I've heard than some mental illness (maybe schizophrenia) is theorized to be in part due to an inability to forget things.
My totally amateur pet theory is that paranoia is threat pattern recognition gone bonkers.
Actually, most of what we do with brains is pattern recognition, and if there isn't enough good input they will make shit up.