Author: Deep Learner
AI and the Future of Health
The emergence of increasingly capable large-scale AI models, such as the recently released GPT-4, is one of the most significant advances in computing in decades. These innovations are rapidly transforming every aspect of the value we get from technology, as demonstrated through Microsoft’s integration of GPT-4 into Bing, Edge, Microsoft 365, Power Platform, GitHub, and other offerings. More recently, Nuance has announced DAX Express, which uses a unique combination of conversational, ambient, and generative AI to automatically draft clinical notes […]
Read moreAI Frontiers: AI for health and the future of research with Peter Lee
Today we’re sitting down with Peter Lee, head of Microsoft Research. Peter and a number of MSR colleagues, including myself, have had the privilege of working to evaluate and experiment with GPT-4 and support its integration into Microsoft products. Peter has also deeply explored the potential application of GPT-4 in health care, where its powerful reasoning and language capabilities could make it a useful copilot for practitioners in patient interaction, managing paperwork, and many other tasks. Welcome to AI Frontiers. […]
Read more
Build a Maze Solver in Python Using Graphs
If you’re up for a little challenge and would like to take your programming skills to the next level, then you’ve come to the right place! In this hands-on tutorial, you’ll practice object-oriented programming, among several other good practices, while building a cool maze solver project in Python. From reading a maze from a binary file, to visualizing it using scalable vector graphics (SVG), to finding the shortest path from the entrance to the exit, you’ll go step by step […]
Read moreResearch Focus: Week of March 27, 2023
Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. In this article NEWS Bing’s gendered translations tackle bias in machine translation Machine translation (MT) models are designed to learn from large amounts of data collected from real-world sources. However, this training
Read more
YAML: Python’s Missing Battery
Python is often marketed as a batteries-included language because it comes with almost everything you’d ever expect from a programming language. This statement is mostly true, as the standard library and the external modules cover a broad spectrum of programming needs. However, Python lacks built-in support for the YAML data format, commonly used for configuration and serialization. In this video course, you’ll learn how to work with YAML in Python using the available third-party libraries, with a focus on PyYAML. […]
Read more
How to Read Python Input as Integers
If you’ve ever coded an interactive text-based application in Python, then you’ve probably found that you need a reliable way of asking the user for integers as input. It’s not enough simply to display a prompt and then gather keystrokes. You must check that the user’s input really represents an integer. If it doesn’t, then your code must react appropriately—typically by repeating the prompt. In this tutorial, you’ll learn how to create a reusable utility function that’ll guarantee valid integer […]
Read more
Speeding up text processing in Python (is hard)
If you’re doing text or string manipulation in Python, what do you do if your code is too slow? Assuming your algorithm is reasonably efficient, the next step is to try faster alternatives to Python: a compiled extension. Unfortunately, this is harder than it seems. Some options don’t offer an easy path to optimizations, others are actually slower. To see this limitation in action, we’ll consider some alternatives: Pure Python, with the default Python interpreter. Cython. mypyc. Rust. Pure Python, […]
Read more