Skip to content
Generic implementations of neural network models and training alogs from scratch
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Implementations of Neural Network models and training algorithms from scratch [WIP]

Models and Algos

  • Feedforward network of arbitrary size and activation functions

  • Backprop with arbitrary cost function

  • Feedback alignment based training for FNNs [1]

  • Recurrent network with arbitrary size and activtion functions

  • Backprop through time [WIP]

  • RNN traninng with feedback alignment [2]


Numpy and Matplotlib - planning to use JAX for some of the grad operations.


[1] Lillicrap, Timothy P., et al. Random synaptic feedback weights support error backpropagation for deep learning. Nature communications 7 (2016): 13276

[2] Murray, J. M. (2018). Local online learning in recurrent networks with random feedback. BioRxiv, 458570.

You can’t perform that action at this time.