DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning · HackerPapers discussions

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by bmc7505

Tue, 26 May 2026 17:22:03 GMT

This topic recently came up at the FLANN workshop [1], and seems to periodically be rediscovered [2,3,4] in different contexts. While some have speculated about the biological role it plays (e.g., Pearlmutter & Houghton [5]), we still lack a conclusive theory of sleep, but the convergent evolution of this specific phenomenon across the animal kingdom and the fact that deprivation is inevitably fatal seems like an important clue. [1]: https://flann.cs.yale.edu [2]: https://www.cs.toronto.edu/~hinton/csc2535/readings/ws.pdf [3]: https://arxiv.org/abs/1711.02282 [4]…

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by erichocean

Sun, 20 Oct 2024 16:27:41 GMT

> So if someone figures out to do this, it will probably take less hardware than an LLM. We have, it's called DreamCoder. There's a paper and everything. Everything needed for AGI exists today, people simply have (incorrect) legacy beliefs about cognition that are holding them back (e.g. "humans are rational"). https://arxiv.org/abs/2006.08381

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — HN submission

Tue, 26 Dec 2023 00:40:43 GMT

DreamCoder: Growing Generalizable, Interpretable Knowledge

83 points; 7 discussion replies on HN. Paper and source history. A submission is not an endorsement.

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by nextos

Sat, 02 Sep 2023 00:24:28 GMT

Some parts of PAIP might be outdated, but it still has really current material on e.g. embedding Prolog in Lisp or building a term-rewriting system. That's relevant for pursuing current neuro-symbolic research, e.g. https://arxiv.org/pdf/2006.08381.pdf. Other parts like coding an Eliza chatbot are indeed outdated. I have read AIMA and followed a long course that used it, but I didn't really like it. I found it too broad and shallow.

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by notacat

Mon, 03 Jul 2023 15:09:43 GMT

AI Research Residency Program (1 year) | Zug/Zurich area | Full time | On site | 100-200k CHF/annum I am launching a new AI research organisation in the Zug/Zurich area. The goal of the organisation is to make a meaningful contribution towards solving AGI. I am looking for employees number no. 1 and 2. This will ideally be someone with a history of interesting research and a clear agenda for future research. I am personally interested in LLM's, MuZero (https://arxiv.org/abs/1911.08265), Dreamer (https://arxiv.org/pdf/2301.04104v1.pdf) and DreamCoder (https://arxiv.org/abs/2006.08381), and…

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by YeGoblynQueenne

Wed, 17 May 2023 10:43:17 GMT

From more recent times, and not specifically an art project, but I liked the work on DreamCoder, particularly the part where it learned to draw in Logo graphics. See figure on page 11 for some graphics: DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning https://arxiv.org/abs/2006.08381

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by YeGoblynQueenne

Thu, 28 Jul 2022 22:43:48 GMT

>> It is current state of art approach. That's not right. The approach described in the article and the linked paper is not "state of the art". It beats one benchmark which has only been used to compare one kind of system: neural program synthesis systems (Codex, AlphaCode, GPT-j and the one in the article, CodeRL). It almost completely fails to acknowledge the wider field of program synthesis that has existed long before that benchmark. The benchmark is ad hoc and arbitrary and it tells us nothing about the general capability of the compared systems, except that they are still very bad at…

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by ahgamut

Tue, 08 Feb 2022 08:45:41 GMT

> I would actually be more impressed if it understood enough about programs to be able to mimic higher-level structure without just memorizing text. Agreed. > Why do you think Python isn't good for comparing program structure? From recent experience I prefer control flow analysis, or something that results in a graph structure. As you said, that's harder with dynamic languages. I also think some Python features (english-like syntax, f-strings, division converts int to float, whitespace indentation, loops vs generator expressions) make structural comparisons messy, but that may just be bias.…

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by bglazer

Thu, 03 Feb 2022 02:01:41 GMT

That’s not entirely correct, as I know of at least one approach to neural program synthesis that employs self supervised learning. https://arxiv.org/abs/2006.08381 It’s a slightly different, easier problem: generating programs based on example outputs, rather than natural language specifications.

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by YeGoblynQueenne

Wed, 02 Feb 2022 20:45:20 GMT

>> This is technology that simply didn't exist in any form 2 years ago. A few examples of neural program synthesis from at least 2 years ago: https://sunblaze-ucb.github.io/program-synthesis/index.html Another example from June 2020: DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning https://arxiv.org/abs/2006.08381 RobustFill, from 2017: RobustFill: Neural Program Learning under Noisy I/O https://www.microsoft.com/en-us/research/wp-content/uploads/... I could go on. And those are only examples from neural program synthesis. Program synthesis…

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by KhoomeiK

Sat, 13 Nov 2021 20:22:52 GMT

> if he could find a way to symbolically represent these fundamental concepts and develop a method by which to combine them logically, then he would be able to generate new thoughts on demand Reminds me of some recent neurosymbolic work, like "DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning" [1] [1] https://arxiv.org/abs/2006.08381

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by YeGoblynQueenne

Mon, 08 Nov 2021 09:25:40 GMT

Program induction (or inductive programming, program synthesis from incomplete specifications etc, the task of learning programs from examples) is not "headed towards ML", it is a branch of machine learning research - only, one that is dominated by symbolic learning approaches such as Inductive Logic Programming and Inductive Functional Programming. When you say "ML" you probably mean the deep neural networks approaches that are currently state of the art for machine vision etc. Deep neural network approaches have been proposed for the task of program induction but they generally lag well…

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by Cybiote

Sun, 29 Aug 2021 06:27:13 GMT

Here is a 1984 article on Eurisko: https://aliciapatterson.org/stories/eurisko-computer-mind-it... From the article we learn Eurisko is more of an example of human machine symbiosis than of AI. "Thus the final crediting of the win should be about 60/40% Lenat/Eurisko," he wrote, "though the significant point here is that neither party could have won alone. The program came up with all the innovative designs and design rules and recognized the significance of most of these. It was a human observer, however, (the author) who appreciated the rest, and who occasionally noticed errors or flaws in…

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by swframe2

Thu, 13 May 2021 02:49:33 GMT

I think https://www.perceptilabs.com/ is a little better. But I hope the future is more like DreamCoder: https://arxiv.org/abs/2006.08381

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — HN submission

Sat, 06 Feb 2021 14:20:48 GMT

DreamCoder, a system that learns to solve problems by writing programs

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by pinouchon

Wed, 09 Dec 2020 14:15:31 GMT

https://arxiv.org/pdf/2006.08381.pdf A take on Josh Tenenbaum's hard problem of learning

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — mentioned by macleginn

Wed, 09 Dec 2020 10:04:30 GMT

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning https://arxiv.org/abs/2006.08381 A killer paper presenting an algorithm capable of inductive learning. ("DreamCoder solves both classic inductive programming tasks and creative tasks such as drawing pictures and building scenes. It rediscovers the basics of modern functional programming, vector algebra and classical physics, including Newton's and Coulomb's laws.")

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

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning — HN submission

Tue, 23 Jun 2020 00:56:20 GMT

DreamCoder: Growing generalizable, interpretable knowledge with program learning

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