Have you ever wanted a guide that explains how to maximize results with #DeepLearning? Introducing The Deep Learning Tuning Playbook, which describes a systematic approach to training and tuning neural networks. Check it out ↓ goo.gle/3QVnqG2
Introducing a new #ReinforcementLearning algorithm for teaching agents how to solve tasks by providing only examples of success, avoiding the need for hand-crafted reward functions while outperforming prior imitation learning approaches. Read more →goo.gle/3vVksX1
Self-Supervised Deep Learning (and semi-supervised and weakly-supervised) making inroads in medical applications.
Labeled data is often scarce in medical applications.
Most deep learning #AI work to date has been supervised. 1. Now we're seeing a trend towards much more unsupervised, aka "self-supervised" (after @ylecun) or weakly supervised.
Figure from @GaryChoy in #DeepMedicine