tdlds

Reducing the temporal-difference learning theory of dopamine to a linear dynamical system

This repository provides code to reproduce the Figures 2 and 3 of Linderman and Gershman, (2016).

References

Linderman, Scott W. and Gershman, Samuel J. "Using computational theory to constrain statistical models of neural data." 2017.

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, ...

Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"

Solving Inverse Physics Problems with Score Matching

Google Colaboratory Notebooks and Repositories (by @firmai)

STATS 305B: Applied Statistics II. Models and Algorithms for Discrete Data.

Machine Learning Methods for Neural Data Analysis

Material for STATS271: Applied Bayesian Statistics (Spring 2021)

High-Resolution Image Synthesis with Latent Diffusion Models

STATS320: Statistical Methods for Neural Data Analysis

discrepancy-based-active-learning