Can anybody recommend any books or resources that would be good for better understanding the mathematical notation that is often seen in ML/DL papers? Preferably with examples of how the notation can be "transcribed" into tensorflow code. I did Linear Algebra and Vector calculus in uni a long time ago but it is a long way back and I would like to get back up to speed with it.

This question I think is not what I am looking for because I would like to see an emphasis on how one can transcribe the math into code.


For a pragmatic introduction to Deep Learning with many Tensorflow code examples I'd recommend

Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition


Deep Learning with Python.

The latter is from 2017 and therefore a bit outdated but a new edition is expected to be published later this year (the author has just finished a draft version).

Both books explain, support or define all concepts with code examples. While there is no literal translation from math to code, I do think they provide the required understanding by directly using code as a notation.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.