Lecun's post is not even a paper as stated in the foreward of the paper. But thanks for bringing it up, i will read it
> This document is not a technical nor scholarly paper in the traditional sense, but a position paper expressing my vision for a path towards intelligent machines that learn more like animals and humans, that can reason and plan, and whose behavior is driven by intrinsic
objectives, rather than by hard-wired programs, external supervision, or external rewards. Many ideas described in this paper (almost all of them) have been formulated by many authors in various contexts in various form. The present piece does not claim priority for any of them but presents a proposal for how to assemble them into a consistent whole. In particular, the piece pinpoints the challenges ahead. It also lists a number of avenues that are likely or unlikely to succeed.
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”.
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
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.
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].
> This document is not a technical nor scholarly paper in the traditional sense, but a position paper expressing my vision for a path towards intelligent machines that learn more like animals and humans, that can reason and plan, and whose behavior is driven by intrinsic objectives, rather than by hard-wired programs, external supervision, or external rewards. Many ideas described in this paper (almost all of them) have been formulated by many authors in various contexts in various form. The present piece does not claim priority for any of them but presents a proposal for how to assemble them into a consistent whole. In particular, the piece pinpoints the challenges ahead. It also lists a number of avenues that are likely or unlikely to succeed.