Microsoft AI Lab

Auf der Microsoft Build 2018 wurde das Microsoft AI Lab angekündigt. Jetzt gibt es endlich mehr Infos dazu. Tara Shankar Jana, Senior Technical Product Marketing Manager at Microsoft, hat im Machine Learning Blogeintrag erste Einblicke in das AI Lab veröffentlicht.

Was ist das Microsoft AI Lab?

Zitat: "AI Lab helps our large fast-growing community of developers get started on AI. It currently houses five projects that showcase the latest in custom vision, attnGAN, Visual Studio tools for AI, Cognitive Search, machine reading comprehension and more. Each lab gives you access to the experimentation playground, source code on GitHub, a crisp developer-friendly video, and insights into the underlying business problem and solution. One of the projects we highlighted at //Build was the search and rescue challenge which gave the opportunity to developers worldwide to use AI School resources to build and deploy their first AI model for a problem involving aerial drones."

Es gibt mehrere Szenarien, die mit dem AI Lab verwirklicht werden können. Im Folgenden wird Machine Reading Comprehension (MRC) vorgestellt.

MRC is all about answering a query about a given context paragraph. MRC requires modeling complex interactions between the context and the query. Using a novel neural network architecture called the Reasoning Network (ReasoNet), Microsoft Researchers were able to mimic the inference process of human readers. With a question in mind, ReasoNets read a document repeatedly, each time focusing on different parts of the document until a satisfying answer is found or formed. Microsoft Researchers today have been able to surpass human-level parity on the SQUAD dataset using an unique MRC algorithm called R-NET: Machine Reading Comprehension With Self-Matching Networks. R-NET applies a self-matching attention mechanism to refine the representation by matching the passage against itself, which effectively encodes information from the whole passage. When we applied these MRC algorithms to the book Future Computed by Harry Shum and Brad Smith. It was incredible to see how many interesting questions we were able to answer using this technique. We can apply this to enterprise data and help customers answer their domain-specific questions.


Was kommt als Nächstes?

Laut Microsoft wird es bald die Möglichkeit geben, eigene Beiträge aus der Community in das AI Lab einzureichen (AI Lab Community Submission). Die Idee ist, die Community miteinzubeziehen und ein Feedback zum AI Lab zu erhalten. Schon jetzt Experimente in das AI Lab eingereicht werden.

Starten Sie heute mit der Benutzung des Microsoft AI Labs unter Viel Spaß!