Skip to content

Latest commit

 

History

74 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Colab-Based Projects

Several of my projects have been work based primarily in Google Colab, and they are collected here. Many of these are still works in progress.

RNN Multiclass

Code for the project resulting in our Geometry of Integration in Text Classification RNNs paper (accepted to ICLR 2021). This work uses tools from dynamical systems analysis to better understand recurrent networks trained on text-classiciation tasks. Note this work relies on the reverse-engineering neural networks (renn) library.

RNN Seq2Seq

Follow-up work to the above that aims to analyze the dynamics of attention in Transformer-like and recurrent architectures. A paper based on this work has been submitted to ICML 2021. (See this for most recent coding samples.)

Echo-State RNN

Also a follow-up to the multi-class RNN work above. I aim to leverage our understanding of how RNNs trained on such tasks behave in order to better understand the efficacy of echo-state networks.

RNN RL

Some early work attempting to apply our dynamical systems analysis to RNNs trained on reinforcement learning tasks.

Large Learning Rates

Large learning rate work that is a follow-up to large learning rate and catapult behavior observed in networks with MSE loss. We aim to extend such results to network with cross-entropy loss.

About

Notebooks from Google Colab

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages