Deep learning

Machine learning methods that use deep Neural networks, which are trained via Stochastic gradient descent in most cases.

Sometimes it can be an unnecessary complexity12.

What are the lessons? Lessons from deep learning

Topics

Courses

Books

Tools

Visualization

Talks and tutorials

Articles

References

Review

Augmenting small datasets with transformations

Noise

Adversarial examples

About baselines

Natural language processing

Binarization

Others


  1. One neuron versus deep learning in aftershock prediction, https://www.nature.com/articles/s41586-019-1582-8 

  2. Rajkomar2018scalable - simple logistic regression performs as well as the deep model. https://twitter.com/ShalitUri/status/1009534668880928769?s=20