Stars
TemporAI: ML-centric Toolkit for Medical Time Series
Newton and Quasi-Newton optimization with PyTorch
Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Machine Learning and Artificial Intelligence for Medicine.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects
Synthetic Control for high dimensional individual treatment effects
Codes for the ICML paper LazyIter: A Fast Algorithm for Counting Markov Equivalent DAGs and Designing Experiments
Sklearn-style implementations of Neural Network-based Conditional Average Treatment Effect (CATE) Estimators.
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
TIme series DiscoverY BENCHmark (tidybench)
Latex code for making neural networks diagrams
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…
Uplift modeling and causal inference with machine learning algorithms
🔬 Research Framework for Single and Multi-Players 🎰 Multi-Arms Bandits (MAB) Algorithms, implementing all the state-of-the-art algorithms for single-player (UCB, KL-UCB, Thompson...) and multi-play…
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
A Python implementation of global optimization with gaussian processes.
A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!
Materials for the practical sessions at EEML2019