Ramin Hasani

lqh. Python

leap-finetune. A full model customization repo for Liquid Foundation Models

gigastep. Python

liquid-s4. Liquid Structural State-Space Models

ncps. PyTorch and TensorFlow implementation of NCP, LTC, and CfC wired neural models

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

evojax. Jupyter Notebook

GoTube. Scalable stochastic verification of continuous-depth models

evosax. Evolution Strategies in JAX 🦎

RFAD. Code for the paper "Efficient Dataset Distillation using Random Feature Approximation"

S5. Python

torchdyn. A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

stability-sdk. SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

stable-diffusion. A latent text-to-image diffusion model

python-binance. Binance Exchange API python implementation for automated trading

PyPortfolioOpt. Financial portfolio optimization in python, including classical efficient frontier, Black-Litterman, Hierarchical Risk Parity

tensorflow-image-models. TensorFlow port of PyTorch Image Models (timm) - image models with pretrained weights.

liquid_time_constant_networks. Code Repository for Liquid Time-Constant Networks (LTCs)

machine-learning-for-trading. Code for Machine Learning for Trading, 3rd edition — from data sourcing to live execution.

CfC. Closed-form Continuous-time Neural Networks

LTC.jl. Julia

pyhopper. PyHopper is a hyperparameter optimizer, made specifically for high-dimensional problems arising in machine learning research.

racing_dreamer. Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

NeuralNetworkArena. TeX

evidential-deep-learning. Learn fast, scalable, and calibrated measures of uncertainty using neural networks!

torch_eunn. A Pytorch implementation of an efficient unitary neural network (https://arxiv.org/abs/1612.05231)

robustness. A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

f1tenth_maps. Collection of f1tenth tracks from various sources

the-pile. Python

darts. Differentiable architecture search for convolutional and recurrent networks

icra_lds. Official code repository of the paper Gershgorin Loss Stabilizes the Recurrent Neural Network Compartment of an End-To-End Robot Learning Scheme by Mathias Lechner, Ramin Hasani, Daniela Rus, and Radu Grosu, published at ICRA 2020.

Optimization.jl. Mathematical Optimization in Julia. Local, global, gradient-based and derivative-free. Linear, Quadratic, Convex, Mixed-Integer, and Nonlinear Optimization in one simple, fast, and differentiable interface.

AirSim. Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

papers-with-annotations. Research papers with annotations, illustrations and explanations

ode-lstms. Code repository of the paper Learning Long-Term Dependencies in Irregularly-Sampled Time Series

ordinary-neural-circuits. Code repo for paper: ICML 2020 paper Natural lottery ticket winner: RL for ordinary neural circuits

gcalcli. Google Calendar Command Line Interface

normalizing-flows. Implementation of normalizing flows in TensorFlow 2 including a small tutorial.

COVID-19. Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE

autonomous_racing_cars. This is the code and lab repository for the course ARC of TU Wien - Reproduced from https://github.com/mlab-upenn/f110-fall2019-skeletons

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

SiamMask. [CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation

ODYNN. Optimization for DYnamic Neural Networks

stanford-cme-102-ordinary-differential-equations. VIP cheatsheets for Stanford's CME 102 Ordinary Differential Equations for Engineers

stanford-cs-229-machine-learning. VIP cheatsheets for Stanford's CS 229 Machine Learning

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

bhtsne. Barnes-Hut t-SNE

ordinary_neural_circuits. Neuronal Circuit Policies

Convolutional-Autoencoder. I train a CAE in Keras

RNN-Training-for-Parking. [Materials and Methods for submission X] This repository contains all the necessary data, for reproducing the RNN training process and monitoring their performance.

SIM-CE. SIM-CE is an advanced, user-friendly modeling and simulation environment in Simulink, for performing multi-scale behavioral analysis of the nervous system of Caenorhabditis elegans (C. elegans).

openworm-experiments. Python

keras. Deep Learning for humans

awesome-deep-vision. A curated list of deep learning resources for computer vision

dcgan_code. Deep Convolutional Generative Adversarial Networks

seq2seq. A general-purpose encoder-decoder framework for Tensorflow

seq2seq. A general-purpose encoder-decoder framework for Tensorflow

Azure-MachineLearning-DataScience. HTML

Worm-Blogging. Here, I include my thoughts about how does the brain of the worm give rise to remarkable behavioral plasticities

arxiv-sanity-preserver. Web interface for browsing, search and filtering recent arxiv submissions

Lasagne. Lightweight library to build and train neural networks in Theano

Lasagne. Lightweight library to build and train neural networks in Theano

Theano. Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

colah.github.io. HTML

OpenWorm. Repository for the main Dockerfile with the OpenWorm software stack and project-wide issues

sibernetic. This is a C++/OpenCL implementation of the PCISPH algorithm supplemented with a set of biomechanics related features applied to C. elegans locomotion

CElegansNeuroML. NeuroML based C elegans model, contained in a neuroConstruct project, as well as c302

nupic-legacy. Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.

Theano. Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor

mxnet. Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

CNTK. Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

caffe. Caffe: a fast open framework for deep learning.

tensorflow. An Open Source Machine Learning Framework for Everyone