Get productive with TensorFlow.js - Google's Machine Learning library for JavaScript. From pre-made off the shelf models to writing or training your own, learn how to create next gen web apps. Are you a web engineer, designer, or creative thinker looking to apply AI or use Machine Learning in your next web application but are unsure where to begin? Or maybe you’re overwhelmed by other courses that focus more on the mathematical proofs than actually enabling you to use these new technologies for real world applications? This course offers a solution and the knowledge to be the "missing manual" for JavaScript users without a background in Machine Learning.
Class Deals by MOOC List - Click here and see EdX's Active Discounts, Deals, and Promo Codes.
Machine Learning (ML) on the web is growing faster than ever so now is the time to take your first steps too. Learn what the difference is between Artificial Intelligence, Machine Learning, and Deep Learning but also how to use such techniques practically through real examples using TensorFlow.js - Google's leading ML library for JavaScript.
Supercharge your next web app with superpowers - from classifying text in a blog post comment to automatically block spam, to using sensors like a webcam on your mobile device to alert you when your dog is on the couch after you left the house. The knowledge you learn could be applied to any business OR creative idea you have for your next project no matter what industry you may be working in.
Better yet, JavaScript is one of few programming languages that can run everywhere enabling you to leverage the knowledge from this course and apply it client side, server side, via native apps, and even IoT devices allowing you to reuse what you learn across multiple environments.
This course aims to educate, inspire, and enable you to rapidly create your next ML powered idea in this rapidly emerging industry while providing you with a solid foundation to understand the field and confidence to explore the industry further.
Web applications are evolving, so sign up, join the fun, and get an edge over the competition. No background in ML is required to take the course. A basic, working knowledge of web technologies such as HTML, CSS, and JavaScript is highly recommended.
This course is part of the Fundamentals of Google AI for Web Based Machine Learning Professional Certificate.
What you'll learn
- Common terms and what they mean
- How Machine Learning works (without formal mathematical definitions)
- Overview of the TensorFlow.js library
- Advantages of using ML in JavaScript
- Ways to consume or create Machine Learning models
- How to use pre-made “off the shelf” models
- What Tensors are in Machine Learning
- How to use Tensors with ML models
- How to write a simple custom model
- Perceptrons (artificial neuron) and how they work
- Linear regression to predict numbers using single neuron
- Multi layered perceptrons for handling more complex data
- How to use models that use Convolutional Neural Networks for images
- How to convert Python models to JavaScript
- Transfer learning - reusing existing trained models with your own data
- Inspiring projects others are creating to seed your own future ideas
Syllabus
- Welcome to TensorFlow.js
1.1 Course overview and how people are applying skills you will learn
1.2 Who is the course aimed at
1.3 Introduce yourself
1.4 What will you be making?
1.5 Your background
- Introduction to ML & TensorFlow.js
2.1 What's the difference - AI / ML / Deep Learning
2.2 Demystifying Machine Learning
2.3 Test your knowledge
2.4 What is TensorFlow.js
2.5 Three ways to use ML
2.6 Test your knowledge
- Using Pre-Made models
3.1 What are pre-made models?
3.2 Selecting the right model to use
3.3 Quiz
3.4 Case study - using a pre-made model for object detection
3.5 Make your own smart security camera
3.6 Loading saved TensorFlow.js models directly
3.7 Tensors in Tensors out
3.8 Coding practice
- Writing custom models
4.1 Rolling your own models
4.2 Starting simple: Predicting a number
4.3 Going deeper: Perceptrons
4.4 Using a perceptron to predict numbers
4.5 Implementing a perceptron for linear regression
4.6 Test your knowledge
4.7 Going deeper: Multi-layered perceptron
4.8 Implementing a multi-layered perceptron
4.9 Training a multi layered perceptron for classification task
4.10 Test your knowledge
4.11 Beyond perceptrons
4.12 Researching other ML architecture types
- Transfer Learning
5.1 Reusing existing models
5.2 Make Teachable Machine yourself
5.3 Project ideas
5.4 Test your knowledge
- Reusing models from Python
6.1 Benefits of model reuse
6.2 Converting Python saved models6.10 Test knowledge
6.3 Convert a model yourself
6.4 Comment Spam detection
6.5 Choosing an appropriate model
6.6 Use converted model to check spam in real application
6.7 Dealing with edge cases
6.8 Retraining a model to deal with custom edge cases
6.9 What models would you convert?
- To the future and beyond
7.1 Machine Learning as a Web Engineer
7.2 Find a friend to continue hacking
7.3 Course summary and how to join the TensorFlow.js community
