Relational inductive biases, deep learning, and graph networks · HackerPapers discussions

Relational inductive biases, deep learning, and graph networks — HN submission

Sat, 21 Dec 2024 17:40:32 GMT

Relational inductive biases, deep learning, and graph networks

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Relational inductive biases, deep learning, and graph networks — mentioned by taliesinb

Sun, 18 Aug 2019 10:17:40 GMT

Hasselt and co, who authored the original Rainbow DQN model that was bested by SimPLe (this paper), responded recently with "When to use parametric models in reinforcement learning?" [1], which is an interesting read. Punchline: "We explain why their [SimPLe's] results may perhaps be considered surprising, and show that in a like-for-like comparison Rainbow DQN outperformed the scores of the model-based agent, with less experience and computation.". In other words, in an apples-to-apples comparison, model-based RL have not been shown to be more sample efficient than suitably optimized DQNs.…

Paper and discussion history. A mention is not an endorsement.

Relational inductive biases, deep learning, and graph networks — HN submission

Sat, 20 Oct 2018 15:25:26 GMT

Relational inductive biases, deep learning, and graph networks

45 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Relational inductive biases, deep learning, and graph networks — mentioned by mlthrowaway1953

Wed, 01 Aug 2018 15:51:04 GMT

Is the Fields Medal going to still be relevant in 10 years, when most of the the major mathematical discoveries are made by deep learning and deep reinforcement learning systems? Already systems are learning to reason about concepts [1] and of course there is classical work on proof checkers [2]. It's very likely that the 2028 Fields medal will be awarded to a programmer, not some mathematical super-genius (assuming that the committee is fair, and not biased against machines). [1] https://arxiv.org/abs/1806.01261 [2] https://en.wikipedia.org/wiki/Four_color_theorem

Paper and discussion history. A mention is not an endorsement.

Relational inductive biases, deep learning, and graph networks — mentioned by blueyes

Fri, 08 Jun 2018 16:38:18 GMT

Chatbots proposed to solve a problem that current technology is bad at: understanding natural language. Very few experts claimed that algorithms could master the combinatorics of natural language beyond a few very narrow domains. On top of the technical risk, the voice and chat UX does not give a lot of visibility to users, as this post points out. What happened was: algorithmic advances in other areas lead to analogous reasoning by non-experts whose self-promotion aligned with the media's need for something new, big and understandable. And then it failed. The irony, of course, is that…

Paper and discussion history. A mention is not an endorsement.