From the course: Machine Learning Foundations: Prototyping with Edge Impulse
Join today to access over 24,400 courses taught by industry experts.
Machine learning workflow - Arduino Tutorial
From the course: Machine Learning Foundations: Prototyping with Edge Impulse
Machine learning workflow
- [Instructor] Machine learning applications, especially for embedded devices, typically involve evaluating input from a sensor and assigning it to one of a set of classes the device expects. A typical machine learning workflow involves several steps that are critical to success. The general steps are problem formulation, data collection, feature engineering, training, evaluation and tuning, and finally, deployment. The first step in a machine learning workflow is to define the problem that needs to be solved. Identify the business or research problem that the machine learning model will address, as well as the data and resources required to solve the problem. The next step is to collect and prepare data that will be used to train a machine learning model. This requires identifying relevant data sources, collecting the data, and cleaning and pre-processing the data to identify mislabeled values, outliers, and other errors. The third step is feature engineering, which involves…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
