ML Bookmarks

Special 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.

Build Neural Nets with another Neural Nets

Additional Resources

Benchmarks

  • DeepBench Benchmarking Deep Learning operations on different hardware

Datasets