Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Outil
Pytorch-wildlife
At the core of our mission is the desire to create a harmonious space where conservation scientists from all over the globe can unite. Where they’re able to share, grow, use datasets and deep learning…
Blog de recherche Microsoft
Measuring dataset similarity using optimal transport
Is FashionMNIST, a dataset of images of clothing items labeled by category, more similar to MNIST or to USPS, both of which are classification datasets of handwritten digits? This is a pretty hard question to…
Vidéo
Geometry-constrained Beamforming Network for end-to-end Farfield Sound Source Separation
Environmental noise, reverberation and interfering speakers negatively affect the quality of the speech signal and therefore degrade the performance of many speech communication systems including automatic speech recognition systems, hearing assistive devices and mobile devices.…
Vidéo
Microsoft Research AI Breakthroughs 2020: 20 minute research talks, Q&A panel, and event wrap-up
20 minute research talks, Q&A panel, and event wrap-up (1:22) Shamsi Iqbal: Micro-productivity: Redefining Productivity to Adapt to a Changing Landscape of Work (22:08) Alex Polozov: Neuro-Symbolic AI and Program Synthesis (45:57) Robert Sim: Privacy…
Outil
Multi-species Bioacoustic Classification
Multi-species bioacoustic classification using deep learning algorithms. With audio recordings collected from rainforests in Puerto Rico, we build a deep learning model that combines transfer learning and pseudo-labeling as a data augmentation technique to: 1)…
Projet
Project Florence-VL
Microsoft Azure Florence-VL aims to develop state-of-the-art vision-language learning technologies to endow computers with an ability to effectively learn from multi-modality data.
Vidéo
Microsoft Research AI Breakthroughs 2020: 20 minute research talks + Q&A panel
20 minute research talks + Q&A panel (0:59) Debadeepta Dey: Efficient Forward Neural Architecture Search (15:45) Subho Mukherjee: Resource-efficient Learning for Neural Language Understanding at Scale (32:50) Jina Suh: Population-Scale Study of Human Needs During…
