1. 15
  1.  

  2. 2
    1. Write the program in a reversible style.
    2. Reverse the program.
    2.5 ????
    3. Insert gradient codes.
    

    Yeah, I think I need to read the paper…

    1. 1

      From glance of it, seems it sugests you don’t need to keep a stack of previous values, therefore, reduces the memory usage (no need of auxiliary memory to store the forward pass computed values). Seems plausible until some computations cannot be reversed?

      1. 1

        Thats also my concern. What are actual use cases of this technology? I guess only computation where the amount of information stays constant are allowed, which would discard many use case. You cant create something from nothing.

        May be a single or multi body physics simulation?

    2. 1

      This repository definitely needs a Tenet reference of some kind. Code inversion might be cooler than time inversion or will lead one to the other? :D Very cool project!