I propose to add a wide variety of models in the model zoo of Flux. Currently, the model zoo lacks the latest architectures and algorithms in Reinforcement Learning. I will fill this gap by including:

  • Dueling Deep Q Network
  • Actor-Critic algorithm
  • AlphaGo

Apart from these, I will implement some interesting research papers which will cover below models:

  • DCGAN
  • Decoupling Neural Interfaces
  • Spatial Transformer Networks

Organization

Student

Tejan Karmali

Mentors

  • Mike Innes
  • Simon Danisch
  • Christopher Rackauckas
  • Stefan Karpinski
close

2018