This session is from a recent three-day workshop on understanding the geometrical structure of deep neural networks.

Deep learning is transforming the field of artificial intelligence, yet it is lacking solid theoretical underpinnings.

This state of affair significantly hinders further progress, as exemplified by time-consuming hyperparameters optimization, or the extraordinary difficulties encountered in adversarial machine learning.

This problem is at the confluence of mathematics, computer science, and practical machine learning. We invite the leaders in these fields to bolster new collaborations and to look for new angles of attack on the mysteries of deep learning.

In this video, find out about the fastest path to quantum development—the Microsoft Quantum Development Kit and the Q# quantum programming language—featuring high-level language constructs, advanced code simulation, debugging, and documentation, and Microsoft’s portfolio of libraries and samples.

Tutorial also includes details on the Microsoft Quantum Katas, exercises designed to teach quantum programming and quantum concepts.

In this era of “Internet of Code”, data and metadata around open source projects are abundantly available.

Here’s an interesting talk by Microsoft Research on AI developing software itself.

While research in program synthesis is not new, deep learning systems that take advantage of large scale code as data is starting to show new promise in improving developer productivity. The availability of GPU machines and cloud-based distributed systems help build deeper networks and scale them to production systems. In addition to passive input from open repos, crowdsourcing software expertise and integrating this with software systems has shown positive results. AI promises assistance and automation in every aspect of software development from edit and build stage to test and deploy stage. What traditional compiler and run time systems did with rules and analyzers can be replaced with AI-driven algorithmic systems. The concept of Software 2.0 is being discussed where code appears as data and where traditional software development processes give way to AI-based systems. In this panel, we explore opportunities for research and technology to improve productivity in software engineering and how AI plays a role in it.

Here’s an interesting talk from Microsoft Research on a quantum computing case study in conjucction with the University of Washington.

Case study: Quantum computing curriculum developed with the University of Washington Recently, our Quantum Software experts partnered with UW to bring a 10-week Introduction to Quantum Computing and Quantum Programming in Q# to the school of Computer Science. Learn how students can get started with hands-on quantum programming quickly by completing a rich collection of quantum programming exercises in Q# (‘coding katas’).

Without good models and the right tools to interpret them, data scientists risk making decisions based on hidden biases, spurious correlations, and false generalizations.

This has led to a rallying cry for model interpretability.

Yet the concept of interpretability remains nebulous, such that researchers and tool designers lack actionable guidelines for how to incorporate interpretability into models and accompanying tools.

This panel discussion hosted by Microsoft Research brings together experts on visualization, machine learning and human interaction to present their views as well as discuss these complicated issues.

This Microsoft Research video covers a new research area is focusing on “microproductivity,” breaking larger tasks down into manageable components conducive to small moments throughout the day.

From the video description:

In this breakout session, we bring together experts from academia and the product side to share their vision of a future where traditional tasks can be accomplished via both focused attention and microproductivity. We will unpack how microproductivity may manifest across different domains and scenarios, identify key challenges in designing for microproductivity, discuss how expected outcomes may be impacted, and put forward an agenda that can move the field toward real-life adaptation.

In case you haven’t already noticed it, PowerPoint now includes AI technologies.

They help people create better presentations and become better presenters. Come see how AI helps make creating presentations quicker and easier with Designer and Presenter Coach.

In this video from Microsoft Research, learn how PowerPoint can listen to you practice and provide helpful tips for improvement.