Agree w @egrefen here, too, but find that no matter how hard I advocate for hybrid models people always think I am arguing against all of ML... I think ML will play a huge role in AGI, but only w proper biases, including representations of operations over variables.
-
-
Replying to @GaryMarcus @egrefen and
Properly understood,
#MachineLearning is the study of the relationship of biases to what can be learned with each (and how to implement them computationally). It's bias, all the way down.1 reply 1 retweet 8 likes -
Replying to @ShlomoArgamon @egrefen and
and yet innateness is a dirty word in ML. amazing.
1 reply 1 retweet 2 likes -
Replying to @gchrupala @GaryMarcus and
Gary, are you really arguing that anything you can't get your ML algorithm to do, you can just build in and declare it to be "innate". It is totally ad hoc science to rely on innateness to solve your machine learning problems.
5 replies 0 retweets 2 likes -
Replying to @tdietterich @gchrupala and
Gary seems to think that nature's evolutionary search has resulted in parameters that cannot be found by any artificial search. The idea is so obviously flawed that it may be driven by motivated reasoning, i.e. an identification with a particular perspective rather than insight.
2 replies 0 retweets 1 like -
Replying to @Plinz @tdietterich and
Parameters? Evolution has built a *system*. In what space does one 'artificially search' for one of those?
2 replies 0 retweets 2 likes -
Replying to @timkindberg @tdietterich and
A system is a machine that can be described by a single global transition function (if the function changes you have a different system). Building a system amounts to traversing the implementation space of transition functions. There is no magic boundary between biology and comp
1 reply 0 retweets 0 likes -
Replying to @Plinz @tdietterich and
Actually a system is an arbitrary concurrent, interactive union of what you describe, including nondeterminism. You're going to search in that space?
2 replies 0 retweets 0 likes -
Replying to @timkindberg @Plinz and
I doubt anyone really thinks that "nature's evolutionary search has resulted in parameters that cannot be found by any artificial search" -- only that the kinds or learning presently used in AI are not 𝒕𝒉𝒂𝒕 kind of search.
1 reply 0 retweets 0 likes
Afaik this thing that nobody really thinks that is actually the point of Marcus and Chollet, when they refer to innateness.
-
-
Replying to @Plinz @timkindberg and
How does it work Retweeted How does it work
We need new insights, to guide our experimentation (call it guided evolution) towards architectures with much more powerful built-in structure. Hinton's critique of CNN is a small step in just that direction:https://twitter.com/generuso/status/1000412922722562050 …
How does it work added,
How does it work @generusoReplying to @xbresson @IntuitMachineA quote from Hinton: "There are a lot of things in which NN are quite unlike the brain and that I believe are making them work not as well as they could... I want to build explicit notion of [natural] entities into the architecture of NN." https://youtu.be/rTawFwUvnLE?t=87 …1 reply 1 retweet 4 likes - 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.