Riley16

scot

Set Cover Optimal Teaching for Sequential Decision Making with Inverse Reinforcement Learning

hebbian_pretraining

Course project with Jay McClelland on Hebbian pre-training for error-driven learning. Includes attempts at reproducing the works of some authors, such as Lillicrap, T. P. et al. Random synaptic feedback weights support error backpropagation for deep learning. Nat. Commun. 7, 13276 doi: 10.1038/ncomms13276 (2016). Also includes a simple neural network framework for personal experimentation.

InfoBiGANs

Implementation of a combination of the BiGAN and InfoGAN architectures.

motor_cognition

Learning Dynamical Models of Motor Cognition - Kalman Filters and RNNs - Project completed for CS221 at Stanford by Libby Zhang and Riley DeHaan.

emergent

This is the new version of the emergent neural network simulation software, written now in Go (golang)

envs

Environments for simulations -- provides various examples that can be adapted

GPc

Gaussian process code in C++ including some implementations of GP-LVM and IVM.

lapack

LAPACK development repository

ProjSpring2017

scikit-learn

scikit-learn: machine learning in Python

vis1d

One-dimensional visual environment for modeling complex visual phenomena without slow rendering times.