Deep Learning for Symbolic Mathematics · HackerPapers discussions

Deep Learning for Symbolic Mathematics — mentioned by MrScruff

Tue, 21 Mar 2023 20:31:00 GMT

I'm not sure anyone is claiming that ChatGPT is going to steal their job. I think most people are just extrapolating the ridiculously steep rate of progression and pondering what the future holds. Sure, maybe we're about to hit a wall. But I'm not seeing any evidence of that as it stands. Also, it's not clear to me why it's impossible for an LLM to learn symbolic manipulation? https://arxiv.org/abs/1912.01412

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

Deep Learning for Symbolic Mathematics — mentioned by visarga

Mon, 02 May 2022 18:58:37 GMT

It's a model mismatch, not an inherent impossibility. A calculator needs to have an adaptive number of intermediate steps. Usually our models have fixed depth, but in auto-regressive modelling the tape can become longer as needed by the stepwise algorithm. Recent models show LMs can do arithmetic, symbolic math and common sense chain-of-thought step by step reasoning and reach much higher accuracies. In other words, we too can't do three digit multiplication in our heads reliably, but can do it much better on paper, step by step. The problem you were mentioning is caused by the bad approach…

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

Deep Learning for Symbolic Mathematics — mentioned by Isinlor

Sun, 23 Aug 2020 21:51:42 GMT

It does lead to intelligence and knowledge of the world. It leads to somewhat similar understanding of the world as our understanding of 4D, quantum mechanics or environment close to a black hole. Pretty bad one, mostly based on repeating whatever we have read about in popular science literature without any intuitive understanding. GPT-3 understanding of physical world is similarly bad. It's just simply a modality not available to the model. But GPT-3 is able to do few-shots learning. If you show it couple of times how to do something it will try to repeat after you showing some rudimentary…

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

Deep Learning for Symbolic Mathematics — mentioned by thomasahle

Tue, 26 May 2020 22:14:09 GMT

They don't actually use trees in the paper though. https://arxiv.org/abs/1912.01412 They express everything in reverse polish notation, exactly so the transformer network can work on streams and not care about the nesting levels. It's a bit odd that this article doesn't talk about that.

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

Deep Learning for Symbolic Mathematics — mentioned by _0ffh

Tue, 26 May 2020 15:38:37 GMT

To me, the article somewhat misses the point of what's interesting here. Using ASTs to represent equations, or even whole programs has plenty of precedents in ML/AI. I'd have liked to know how exactly they translate these trees to a representation suitable for an ANN. Fortunately, the paper seems to be easy to find and access (it's [1], I guess). [1] https://arxiv.org/abs/1912.01412

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

Deep Learning for Symbolic Mathematics — mentioned by thomasahle

Wed, 11 Mar 2020 12:08:40 GMT

Post by the researchers (Facebook AI): https://ai.facebook.com/blog/using-neural-networks-to-solve-... Arxiv paper: https://arxiv.org/pdf/1912.01412.pdf

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

Deep Learning for Symbolic Mathematics — HN submission

Thu, 16 Jan 2020 06:04:48 GMT

Deep Learning for Symbolic Mathematics

5 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Deep Learning for Symbolic Mathematics — mentioned by sarosh

Wed, 15 Jan 2020 20:56:00 GMT

Actual paper is at https://arxiv.org/pdf/1912.01412.pdf

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

Deep Learning for Symbolic Mathematics — HN submission

Fri, 20 Dec 2019 03:04:11 GMT

Deep Learning for Symbolic Mathematics

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

Deep Learning for Symbolic Mathematics — HN submission

Tue, 17 Dec 2019 20:30:24 GMT

Deep Learning for Symbolic Mathematics – NN that can do advanced math [Facebook]

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

Deep Learning for Symbolic Mathematics — HN submission

Thu, 05 Dec 2019 21:06:36 GMT

Deep Learning outperforms Mathematica on symbolic integration and solving ODEs

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.