Why AI must learn to forget

#1
C C Offline
Machines with perfect memory would be dangerous
https://iai.tv/articles/why-ai-must-lear...-auid-2302

EXCERPTS: . . . First of all, building Artificial Intelligence with infallible memory systems is unlikely to be feasible, for similar reasons that infallible memory isn’t feasible in us. There are simply practical limits on the amount of information that can be stored and processed in a finite system. But even if it were possible, to build infallible memory into machines would mean forgoing some of the important benefits of forgetting.

I said above that forgetting is sometimes harmful in its effects on other people. But there are also times when it’s beneficial. For instance, you probably know someone who just won’t let things go...

[...] In many cases, the philosopher Rima Basu argues, we have a duty to forget. [...] As Basu says, ‘you cannot truly forgive if the wrongdoing is still at the forefront of your mind’. Other cases include those where you learn something in a way which violates another’s right to privacy...

[...] In all these scenarios, we might wish that the people around us were more forgetful. And as frustrating as it can be when other people remember too much, it has the potential to be much more harmful when AI systems do it. There are already significant concerns about the amount of our personal data available to AI systems, given the control they exert over our lives. The situation could be made even more troublesome by systems which stored all of the information they encountered about us indefinitely. This alone is a reason to think about building forgetful machines.

But there are other reasons to consider this – reasons which are ‘internal’ to the project of building artificial intelligence. Above, I said that forgetting strikes us as a cognitive vice: that our memory systems are supposed to retain information, and that forgetting is a sign that our memory systems carry out this function only imperfectly. But perhaps that’s not quite right: perhaps, to some extent, we’re supposed to forget.

The philosopher Kirk Michaelian has argued that this is the case: that a well-constructed memory system ought to forget certain things. The idea is that memory isn’t only a storage facility; it also centrally involves retrieval. For memory to work well, we need to be able to retrieve the information we need when we need it. This will be harder to the extent that our memory ‘storage’ is full of information we’re never likely to need. So, Michaelian argues, a virtuous memory system will be one which prioritises the important things forremembering, preferentially forgetting ‘uninteresting’ records – as our memory systems, at least approximately, do.

So, might forgetting actually be beneficial to artificial agents too? In at least some cases, it seems the answer is ‘yes’... (MORE - missing details)
Reply
#2
confused2 Offline
Are 'they' suggesting.. bank accounts are one of the more important tokens of value of a human being - far more important than 'reputation' or (unless actually imprisoned, tortured or killed) anything else. Your luxury yacht no longer yours. The title to your house and ownership of your SUV suddenly forgotten. Can't see it working. The best way round forgiveness is not doing whatever it was and if you want to be 'forgiven' or merely tolerated - choose the people you associate with accordingly. Fortunately (hopefully) this site is a tolerant and forgiving corner of the Everse.
Reply


Possibly Related Threads…
Thread Author Replies Views Last Post
  Neurons in a dish learn to play Pong. What does it mean? Ethical concerns? C C 0 23 Feb 23, 2022 07:45 PM
Last Post: C C
  It takes a lot of energy for machines to learn Leigha 4 205 Jan 15, 2021 02:06 PM
Last Post: confused2
Question Can a robot learn right from wrong? Leigha 7 438 Jul 14, 2019 07:05 PM
Last Post: Leigha
  What artificial brains can teach us about how real brains learn C C 1 267 Oct 1, 2017 11:22 PM
Last Post: Syne
  Artificial intelligence researchers must learn ethics C C 0 396 Sep 1, 2017 05:39 PM
Last Post: C C
  Electronic synapses that can learn: Towards an artificial brain? C C 0 340 Apr 4, 2017 03:40 AM
Last Post: C C
  Can satellites learn to 'see' poverty? + Internet: the world wide cage? C C 1 372 Aug 31, 2016 03:47 AM
Last Post: scheherazade
  7 unexpected outcomes of the singularity + When machines learn like humans: The end? C C 1 677 Dec 15, 2015 11:38 PM
Last Post: Magical Realist
  Physical nature of computers may reveal deep truths + How machines learn and you win C C 0 763 Dec 6, 2015 10:06 PM
Last Post: C C



Users browsing this thread: 1 Guest(s)