Adapted from the recently released O'Reilly book Deep Learning for the Life Sciences, one of its author (general partner at a16z) shares the three biggest questions the practitioner wanting to use AI in the life sciences should be thinking about. Here is the link to the article.

You can also listen to the podcast episode.

Improved search features, batched logging of metrics, and much more. Learn more in the release blog.

PyTorch just launched PyTorch Hub, a pre-trained model repository designed to facilitate research reproducibility.

Sebastian Raschka, the author of Python Machine Learning from Packt Publishing recently release this amazing collection of notebooks that contain implementations of deep learning architectures in TensorFlow and PyTorch.

Along with LIME, SHapley Additive exPlanations is one of most prominent techniques for Machine Learning model interpretability. This blog post uses the data from Stack Overflow latest developer survey and machine learning techniques to uncover bias within the data.

GANs are notoriously hard to train, in this article, Jason from Machine Learning Mastery has compiled a list of empirical heuristics, tips and tricks to help you make them converge.

I recently discovered the blog of Divam Gupta, research fellow at Microsoft Research. Interesting choice of topics and a good mix between introductory theory and practical code implementations. Take a look at:

Did we miss any good stuff? Tell us at [email protected]

Want to share any article or learning resource you think deserves a spot in the issue? [email protected]