Overview
TensorFlow.js is a JavaScript framework for machine learning. TensorFlow.js enables users to build and train machine learning models directly in JavaScript.
This instructor-led, live training (online or onsite) is aimed at data scientists who wish to use TensorFlow.js to identify patterns and generate predictions through machine learning models.
By the end of this training, participants will be able to:
- Build and train machine learning models with TensorFlow.js.
- Run machine learning models in the browser or under Node.js.
- Retrain pre-existing machine learning models using custom data.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Requirements
- JavaScript programming experience
Audience
- Data Scientists
Course Outline
Introduction
TensorFlow.js Overview
- What is TensorFlow.js
- TensorFlow features
- Math operations and memory management
Preparing the Development Environment
- Installing and configuring TensorFlow.js
Running TensorFlow.js
- Running TensorFlow.js on a browser
- Running TensorFlow.js under Node.js
Data Preparation
- Reading and writing to data
- Preparing features
- Labeling data
- Normalizing data
- Splitting data into test data and training data
Machine Learning Models
- Creating a model
- Creating layers
- Compiling a model
Training and Testing
- Training models
- Testing models
Predictions and Regressions
- Integrating a UI
- Loading a model
- Visualizing predictions
- Creating regressions
Classifications
- Working with binary classification
- Working with multi-class classification
Summary and Conclusion