5

I want to implement Direct Feedback Alignemnt in Tensorflow.

Reference paper: https://arxiv.org/pdf/1609.01596v5.pdf, Nøkland (2016)

I implemented a simple network that does DFA in pure Python, having explicitly the backprop, I just switched the backward pass of BP with the one of DFA.

Backward passes

where B1 and B2 are two random matrices with appropriate dimensions.

Tensorflow training obviously does backprop by default. Where and what should I modify in Tensorflow code in order to get this training behavior?

iacolippo
  • 4,133
  • 25
  • 37
  • 1
    https://github.com/sangyi92/feedback_alignment – Dadep May 12 '17 at 16:54
  • 1
    You could take example from the https://github.com/xuexue/randombp tensorflow implementation where optimisation step is manually defined using Direct Feedback Alignment, instead of using the automatic GradientDescentOptimizer method. – Jean-Marc Aug 06 '17 at 05:27

0 Answers0