a tumblelog
Wed 11 Mar 2020

Solving Differential Equations with Transformers

In this article, I will cover a new Neural Network approach to solving 1st and 2nd order Ordinary Differential Equations, introduced in Guillaume Lample and François Charton (Facebook AI Research)’s ICLR 2020 spotlight paper, “Deep Learning for Symbolic Mathematics”. This paper tackles symbolic computation tasks of integration and solving 1st & 2nd order ODEs with a seq2seq Transformer, we will focus on the latter today.

Source: Solving Differential Equations with Transformers: Deep Learning for Symbolic Mathematics, an article by Ching Lam Choi.

Do not log

Almost every week I accidentally get into this logging argument. Here’s the problem: people tend to log different things and call it a best-practice. And I am not sure why. When I start discussing this with other people I always end up repeating the exact same ideas over and over again.

So. Today I want to criticize the whole logging culture and provide a bunch of alternatives.

Source: Do not log, an article by Nikita Sobolev.

Haskell with UTF-8

Bad news: something is wrong. Good news: it is not necessarily an issue with your code, it can be one of the libraries or build tools that you depend on.

Source: Haskell with UTF-8, an article by Kirill Elagin.