An implementation of Olshausen and Field (96) in PyTorch

NumPy implementation of infinite latent feature model (aka Indian Buffet Process or IBP)

Hierarchical Dirichlet Process Generalized Linear Models

Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filte…

code for KalmanNet

In this project, a simple Nested Chinese Restaurant Process is implemented. this is done by using HLDA for topic modeling with Gibbs Sampler. this project demonstrates the BBC Insight Dataset for e…

Mamba SSM architecture

Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022

This repository contains research code for the paper "Generating realistic neurophysiological time series with denoising diffusion probabilistic models".

A modular RL library to fine-tune language models to human preferences

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

Inference code for Llama models

olfactory (multi-trial GPLVM)

Implemenation of Manifold Inference from Neural Dynamics (MIND) from Low & Lewallen et. al, '18

Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"

Lightweight, useful implementation of conformal prediction on real data.

A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

Gaussian processes framework in python

Fast approximate inference for Poisson GLMs

Python codes used in "Structured Recognition for Generative Models with Explaining Away"

Online inference for the Hierarchical Dirichlet Process. Fits hierarchical Dirichlet process topic models to massive data. The algorithm determines the number of topics.

A set of 13 diverse machine-learning tasks that require memory to solve.

Pytorch version of Dreamer, which follows the original TF v2 codes.

A pytorch reprelication of the model-based reinforcement learning algorithm MBPO