Investigate passive and active investing strategies for major world stock indexes

low code backtesting library utilizing pandas and technical analysis indicators

Predicting stock prices using a TensorFlow LSTM (long short-term memory) neural network for times series forecasting

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

FBPCP (Facebook Private Computation Platform) is a secure, privacy safe and scalable architecture to deploy MPC (Multi Party Computation) applications in a distributed way on virtual private clouds…

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

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…

Official code for the paper "Task2Vec: Task Embedding for Meta-Learning" (https://arxiv.org/abs/1902.03545, ICCV 2019)

A Pytorch implementation of DeepCrack and RoadNet projects.

Introduction to Secure Multi-Party Computations

Versatile framework for multi-party computation

MPyC: Multiparty Computation in Python

Global-Scale Secure Multiparty Computation

Biological evolution simulator

1st place solution to the MIIA Deep Learning Hackathon

The project uses Unet-based improved networks to study road crack segmentation, which is based on keras.

Attention Aggregation Framework in PyTorch, ECCV Workshops 2020

Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas…

To classify trades into buyer- and seller-initiated.

Code for experiments in my blog post on the Neural Tangent Kernel: https://eigentales.com/NTK

Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes"

Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube

Computational Physics

Code used for experiments in https://arxiv.org/abs/2008.08601

This tool should help discover different patterns based on similarity measures in historical (financial) data

Script used to download data for stocks.

fastquant — Backtest and optimize your ML trading strategies with only 3 lines of code!

Code to find the best stocks for algo-trading.

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes (CVPR 2021 Oral)