True Positive Weekly #37

The most important artificial intelligence and machine learning links of the week

Hey, in this issue: how computationally complex is a single neuron; an introduction to machine learning compilers and optimizers; a Python library for online machine learning; a tutorial on Gaussian processes; textless NLP; a lightweight Python library for AutoML; and more.

• How computationally complex is a single biological neuron?

• [Tutorial] A friendly introduction to machine learning compilers and optimizers

• [Project] baal: a library to enable Bayesian active learning in your research or labeling work

• [Project] River: a Python library for online machine learning

• [Tutorial] Gaussian processes from scratch

• Textless NLP: Generating expressive speech from raw audio (paper, paper, paper, code)

• [Project] TensorFlow Similarity: a python package designed to make it easy and fast to train similarity models using TensorFlow

• [Project] FLAML: a lightweight Python library that finds accurate machine learning models automatically, efficiently, and economically

Enjoy the newsletter? Help us make it bigger and better by sharing it with your colleagues and friends.

Have a nice weekend! See you next week. — Andriy