Hao Ni's Projects
A collection of resources regarding the interplay between differential equations, dynamical systems, deep learning, control and optimization.
Use Deep Q learning algorithm to do trading. And then use DRL combined with the signature feature set of the p lagged value of spot price to improve the existing algorithm.
A fast and lightweight AutoML library.
Folder / directory structure options and naming conventions for software projects
Calculations in tensor space for Python
Constrained optimization toolkit for PyTorch
Deep Learning for humans
📋 Survey papers summarizing advances in deep learning, NLP, CV, graphs, reinforcement learning, recommendations, graphs, etc.
Models and examples built with TensorFlow
Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
A Sklearn-like Framework for Hyperparameter Tuning and AutoML in Deep Learning projects. Finally have the right abstractions and design patterns to properly do AutoML. Let your pipeline steps have hyperparameter spaces. Enable checkpoints to cut duplicate calculations. Go from research to production environment easily.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
A rewrite, with improvements, of our submission to the PhysioNet 2019 sepsis detection challenge.