Our new paper, Deep Learning for Symbolic Mathematics, is now on arXiv We added *a lot* of new results compared to the original submission. With (1/7)
Amazing results applying transformers to symbolic function integration and differential equations solving by Guillaume Lample and François Charton from FAIR-Paris. Succeeds in many cases where Mathematica fails. Paper:...
Transformers work wonders on natural language. Given enough examples, they can translate without a dictionary. Why not consider mathematics as a language and problem solving as translation tasks? with
Impressive. Sequence to sequence NNs doing symbolic math better than mathematica