Research
Discover an index of datasets, SDKs, APIs and open-source tools developed by Microsoft researchers and shared with the global academic community below. These experimental technologies—available through Azure AI Foundry Labs (opens in new tab)—offer a glimpse into the future of AI innovation.
nlg-eval Evaluation code for various unsupervised automated metrics for NLG (Natural Language Generation). It takes as input a hypothesis file, and one or more references files and outputs values of metrics. Rows across these files…
This is a client which provides LTE access, via a small/femto cell, by communicating with a TVWSDB to negotiate a spectrum.
Hybrid Reward Architecture (HRA) code for the first experiment in the paper located at https://arxiv.org/abs/1706.04208 (opens in new tab).
The Embedded Learning Library (ELL) allows you to design and deploy intelligent machine-learned models onto resource constrained platforms and small single-board computers, like Raspberry Pi, Arduino, and micro:bit. The deployed models run locally, without requiring…
This template shows how to incorporate a vega-lite specification as a PowerBI custom visual.
Neural Phrase-based Machine Translation (NPMT) explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a…
Microsoft Hands-Free Sound Machine is a WPF XAML application that works with a number of Tobii eye tracking devices and leverages the audio and MIDI APIs in Windows 10 to play both sampled audio and…
MMdnn is a comprehensive, cross-framework solution to convert, visualize and diagnosis deep neural network models. The “MM” in MMdnn stands for model management and “dnn” is an acronym for deep neural network. Basically, it converts…