fbpx
Introduction to PyTorch
Recently, Microsoft and PyTorch announced a “PyTorch Fundamentals” tutorial, which you can find on Microsoft’s site and on PyTorch’s site. The code in this post is based on the code appearing in that tutorial, and forms the foundation for a series of other posts, where I’ll explore other... Read more
Model Performance Optimization with TorchServe
In this blog, we are going to take a look at TorchServe, a feature-rich framework for serving machine learning models. We will go through a variety of experiments to test the performance on different operating systems, thread settings, and a number of workers to discover the... Read more
Optimizing PyTorch Performance: Batch Size with PyTorch Profiler
This tutorial demonstrates a few features of  PyTorch Profiler that have been released in v1.9. PyTorch. Profiler is a set of tools that allow you to measure the training performance and resource consumption of your PyTorch model. This tool will help you diagnose and fix machine learning performance issues regardless of whether you are working on one or... Read more
In the previous post you got an overview about interpretability, and the different explainers available in the Interpret-Text tool. In this post, you will get an understanding of how to use one of the explainers: Unified Information Explainer. The Unified Information Explainer can be used when a... Read more
In the previous post, you got an overview about interpretability, and the different explainers available in the Interpret-Text tool. In this post you will get an understanding of how to use one of the explainers: Introspective Rationale Explainer. To generate an outstanding text fragment of important features... Read more
In the previous post you got an overview of interpretability, and the different explainers available in the Interpret-Text tool. In this post, you will get an understanding of how to use one of the explainers: Classical Text Explainer. The Classical Text Explainer is an interpretability technique used... Read more
Accelerate your NLP pipelines using Hugging Face Transformers and ONNX Runtime
This post was written by Morgan Funtowicz from Hugging Face and Tianlei Wu from Microsoft Transformer models have taken the world of natural language processing (NLP) by storm. They went from beating all the research benchmarks to getting adopted for production by a growing number of companies in a record... Read more
Responsible AI: Interpret-Text
Artificial intelligence (AI) systems have a growing impact on people’s lives on an every-day-level, thus it is fundamental to protect people, understand models, and control ai systems. While machine learning (ML) services are constantly developing, Microsoft emphasizes the ethical principles that put people first, meaning that employees are... Read more
WhiteNoise is the newly available Differential Privacy System by OpenDP.  The intent of Differential Privacy is to preserve the security of personally identifiable information & prevent against database reconstruction attacks.  The methods provided by the WhiteNoise system are part of a toolkit that enables researchers to... Read more
How to Assess AI Systems’ Fairness and Mitigate Any Observed Unfairness Issues
This article discusses how we can assess AI systems’ fairness. As we are leveraging data for making significant decisions that affect individual lives in domains such as health care, justice, finance, education, marketing, and employment, it is important to ensure the safe, ethical, and responsible use... Read more