By Quantiphi, Inc. This article describes how Quantiphi leveraged Google Cloud to build an end-to-end machine learning ML pipeline for a global manufacturing client to help them design brake pad materials. This ultimately let the client predict material composition that led to optimized friction performance through a virtual material testing framework. The following sections elaborate on each of these processes in the customer solution created by Quantiphi. The customer was interested in testing friction for brake pads and had sensors attached to testing devices.
Applied Machine Learning: Industry Case Study with TensorFlow - Learn Interactively
I wrote this notebook as a case study to learn TensorFlow Probability. The problem I chose to solve is estimating a covariance matrix for samples of a 2-D mean 0 Gaussian random variable. The problem has a couple of nice features:. I decided to write my experiences up as I went along.
AI software stack inspection with Thoth and TensorFlow
Project Thoth develops open source tools that enhance the day-to-day life of developers and data scientists. Thoth uses machine-generated knowledge to boost the performance, security, and quality of your applications using artificial intelligence AI through reinforcement learning RL. This machine-learning approach is implemented in Thoth adviser if you want to know more, click here and it is used by Thoth integrations to provide the software stack based on user inputs. In this article, I introduce a case study—a recent inspection of a runtime issue when importing TensorFlow 2.
In our workflow, we will:. Our purpose is to demonstrate usage of the MinDiff technique with a very minimal workflow, not to lay out a principled approach to fairness in machine learning. As such, our evaluation will only focus on one sensitive category and a single metric. In a production setting, you would want to approach each of these with rigor. For more information on evaluating for fairness, see this guide.