From the course: Leveraging Cloud-Based Machine Learning on Azure: Real-World Applications

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Manufacturing

Manufacturing

- [Instructor] So let's look at a machine learning use case and this time we'll look at manufacturing. So again, we're dealing with inputs, models and outputs. On inputs we have factory data, and we have rejects. In other words, manufacturing information about what's being processed in a factory and also information about what is being rejected. Quality control is pushing it back and having a particular product to be redone. We're able to model factory behavior, what the factory is doing to create a successful outcome, no rejects as well as rejects. And then the output we're looking to create reject prevention, the ability to proactively spot and solve rejection problems, and the ability to deal with proactive training and maintenance to get to a lower reject rate. So the solution is we're ingesting data, and this time we're leveraging reinforcement learning. And so we're having the knowledge engine basically try to move…

Contents