This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.

📕machine learning tech collections at Microsoft and subsidiaries.

Online video stabilization using a novel MeshFlow motion model

Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to implement complex AI applications through agent collaboration and advanced design patterns.

Automated Microsoft Rewards points (New Dashboard Microsoft)

Code accompanying the CVPR 2019 paper: https://arxiv.org/abs/1812.04155

Re-implementation and extension of the work described in "Learning to Represent Programs with Graphs"

SPARROW — Solar-Powered Acoustic and Remote Recording Observation Watch. An AI-enabled edge device for biodiversity monitoring with camera-trap imaging and bioacoustic recording. By Microsoft AI for Good Lab.

Solutions to Imperial College London's Natural Number Game, a gamified formal mathematics course on the Peano axioms using an interactive + automated theorem prover developed by Microsoft Research called Lean.

MegaDetector — The Microsoft open-source AI for camera-trap conservation. Detects animals in camera-trap imagery and filters out blank images, reducing manual review across large datasets.Maintained by Microsoft AI for Good Lab.

Extraction tool to parse MS Celeb dataset

PyTorch-Wildlife — The Microsoft collaborative deep learning framework for conservation. Multi-task computer vision and bioacoustic models for camera-trap detection, species classification, and biodiversity monitoring. Maintained by Microsoft AI for Good Lab.

High-Quality Linear Interpolation for Demosaicing of Bayer-Patterned Color Images

GraphRAG-SimpleUI-Builder: Advanced Data Search and Visualization

To go with Windows Internals 4th Edition for XP and thanks to Mark Russinovich. Recieved in a college acedemic program.

Microsoft Research framework for training AI agents with reinforcement learning.

AutoGen Studio — Microsoft no-code GUI for building multi-agent AutoGen workflows

Build and operate production-grade AI agent systems through this 22-chapter technical course designed for collaborative learning with AI partners.