News for hackers. Stuff that matters.
Re:LeCun's 2022 paper on autonomous machine intelligence doe... by IfOnlyYouKnew on Thursday July 07, 2022 @10:14AM (#32014381)
Well you can’t just state “this isn’t a paper” at a beginning of a paper to get an exemption from the rules and traditions of scientific discourse. It’s like the people believing it’s not a crime to pay with counterfeit money if the signature reads “Donald Duck”.
Re:LeCun's 2022 paper on autonomous machine intelligence doe... by seydor on Thursday July 07, 2022 @10:48AM (#32014809)
It s not the same at all. You can make a blog post or an HN comment, or really anything and put it out there without following the rules of science journals. This is the essentially a blog post in PDF
Re:LeCun's 2022 paper on autonomous machine intelligence doe... by ironrabbit on Thursday July 07, 2022 @12:03PM (#32015738)
It's a position paper, academics publish them all the time, they're very much a part of scientific discourse. Just different than an experimental results paper.
Re:LeCun's 2022 paper on autonomous machine intelligence doe... by P-NP on Monday July 18, 2022 @05:41AM (#32136298)
It's actually on an academic review site called OpenReview where the dispute is ongoing: https://openreview.net/forum?id=BZ5a1r-kVsf

LeCun claims four "main original contributions" and Schmidhuber basically debunks them one by one, for example:

> (IV) your predictive differentiable models "for hierarchical planning under uncertainty" - you write: "One question that is left unanswered is how the configurator can learn to decompose a complex task into a sequence of subgoals that can individually be accomplished by the agent. I shall leave this question open for future investigation."

> Far from a future investigation, I published exactly this over 3 decades ago: a controller NN gets extra command inputs of the form (start, goal). An evaluator NN learns to predict the expected costs of going from start to goal. A differentiable (R)NN-based subgoal generator also sees (start, goal), and uses (copies of) the evaluator NN to learn by gradient descent a sequence of cost-minimizing intermediate subgoals [HRL1].

It will be interesting to follow this.