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 graphical models and potential outcomes frameworks.
Обновлено 2024-11-21 01:27:34 +03:00
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Обновлено 2024-11-20 05:08:56 +03:00
Hummingbird compiles trained ML models into tensor computation for faster inference.
Обновлено 2024-11-16 00:52:33 +03:00
Workflow that takes advantage of GATKs CNN tool which is a deep learning approach to filter variants based on Convolutional Neural Networks
Обновлено 2024-11-06 01:27:52 +03:00
🐦 Social sharing via Facebook, Twitter & more
Обновлено 2024-11-04 05:45:22 +03:00
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Обновлено 2024-10-28 14:18:34 +03:00
Python package for graph statistics
Обновлено 2024-10-09 19:41:04 +03:00
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
Обновлено 2024-09-04 00:17:43 +03:00
A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.
Обновлено 2024-07-31 00:16:53 +03:00
A python library for intelligently building networks and network embeddings, and for analyzing connected data.
Обновлено 2024-07-11 21:49:18 +03:00
graspologic-native is a library of rust components to add additional capability to graspologic (https://github.com/microsoft/graspologic), a python library for intelligently building networks and network embeddings, and for analyzing connected data.
Обновлено 2024-01-25 21:02:12 +03:00
CryptoNets is a demonstration of the use of Neural-Networks over data encrypted with Homomorphic Encryption. Homomorphic Encryptions allow performing operations such as addition and multiplication over data while it is encrypted. Therefore, it allows keeping data private while outsourcing computation (see here and here for more about Homomorphic Encryptions and its applications). This project demonstrates the use of Homomorphic Encryption for outsourcing neural-network predictions. The scenario in mind is a provider that would like to provide Prediction as a Service (PaaS) but the data for which predictions are needed may be private. This may be the case in fields such as health or finance. By using CryptoNets, the user of the service can encrypt their data using Homomorphic Encryption and send only the encrypted message to the service provider. Since Homomorphic Encryptions allow the provider to operate on the data while it is encrypted, the provider can make predictions using a pre-trained Neural-Network while the data remains encrypted throughout the process and finaly send the prediction to the user who can decrypt the results. During the process the service provider does not learn anything about the data that was used, the prediction that was made or any intermediate result since everything is encrypted throughout the process. This project uses the Simple Encrypted Arithmetic Library SEAL version 3.2.1 implementation of Homomorphic Encryption developed in Microsoft Research.
Обновлено 2023-11-16 20:25:07 +03:00
A web app to create and browse text visualizations for automated customer listening.
Обновлено 2023-10-27 06:29:49 +03:00
A website for exploring the Metropolitan Museum of Art's collection with Generative Adversarial Networks
Обновлено 2023-10-25 18:00:46 +03:00
Firefox Translations is a webextension that enables client side translations for web browsers.
Обновлено 2023-09-04 12:30:18 +03:00
TensorFlow 2 library implementing Graph Neural Networks
Обновлено 2023-07-13 16:47:00 +03:00
Multi-Task Deep Neural Networks for Natural Language Understanding
Обновлено 2023-06-13 00:28:35 +03:00
Running the most popular deep learning frameworks on Azure Batch AI
Обновлено 2023-06-12 22:32:13 +03:00
High performance container overlay networks on Linux. Enabling RDMA (on both InfiniBand and RoCE) and accelerating TCP to bare metal performance. Freeflow requires zero modification on application code/binary.
Обновлено 2023-06-12 22:30:21 +03:00
We design an effective Relation-Aware Global Attention (RGA) module for CNNs to globally infer the attention.
Обновлено 2023-06-12 21:55:25 +03:00
View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition
Обновлено 2023-06-12 21:55:25 +03:00
The Confidential Consortium Blockchain Framework is an open-source system that enables high-scale, confidential blockchain networks that meet all key enterprise requirements—providing a means to accelerate production enterprise adoption of blockchain technology.
Обновлено 2023-05-31 21:49:10 +03:00
Tools for programming chemical reaction networks (CRN), DNA strand-displacement circuits (DSD) and genetically engineered circuits (GEC).
Обновлено 2023-04-23 00:50:20 +03:00
Ruby SDK for Azure Resource Manager: build and manage your Azure cloud infrastructure (Compute, Virtual Networks, Storage, etc...) using Ruby.
Обновлено 2023-01-10 21:02:52 +03:00
TensorFlow implementations of Graph Neural Networks
Обновлено 2022-11-28 22:09:39 +03:00
Source code for paper Conservative Uncertainty Estimation By Fitting Prior Networks (ICLR 2020)
Обновлено 2022-11-28 22:09:08 +03:00
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
Обновлено 2022-09-23 17:06:50 +03:00
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
Обновлено 2022-08-30 12:45:51 +03:00
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
Обновлено 2022-08-30 11:00:20 +03:00