ML Bookmarks

This is the list of some useful papers or resources with short explanation

Build Neural Nets with another Neural Nets

Reinforcement Learning

  • Progressive Neural Networks progressive networks approach immune to forgetting and can leverage prior knowledge via lateral connections to previously learned features.
  • Reward Augmented Maximum Likelihood for Neural Structured Prediction (Short Summary)This paper presents a simple and computationally efficient approach to incorporate task reward into a maximum likelihood framework. We establish a connection between the log-likelihood and regularized expected reward objectives, showing that at a zero temperature, they are approximately equivalent in the vicinity of the optimal solution.

Other Topics

One Shot Learning


  • DeepBench Benchmarking Deep Learning operations on different hardware