Machine Learning for Web Developers (Web ML)

Channel: Google for Developers

Videos (47)

1 — 1.1: Machine Learning for Web Devs & Creatives (Web ML) - Next gen web apps with TensorFlow.js
2 — 1.2: Who is the course aimed at? Anyone who knows JavaScript. Creatives, Web Devs, Artists
3 — 1.3: What will you learn in this Web ML course?
4 — 2.1: Artificial Intelligence, Machine Learning, and Deep Learning
5 — 2.2: Demystifying Machine Learning
6 — 2.3: How to train Machine Learning systems?
7 — 2.4: What is TensorFlow.js? (JavaScript + Machine Learning)
8 — 2.5: 3 ways to use Machine Learning on the web with TensorFlow.js
9 — 3.2: Selecting an ML model to use
10 — 3.1: What are pre-trained models?
11 — 3.3.1: Make your own web based smart camera in JS - Part 1
12 — 3.3.3: Make your own web based smart camera in JS - Part 3
13 — 3.3.2: Make your own web based smart camera in JS - Part 2
14 — 3.3.4: Make your own web based smart camera in JS - Part 4
15 — 3.3.6: Make your own web based smart camera in JS - Part 6
16 — 3.3.5: Make your own web based smart camera in JS - Part 5
17 — 3.6.1: Using advanced pre-trained Web ML models - Part 1: TensorFlow Hub usage
18 — 3.5: Using a simple raw TensorFlow.js pre-trained saved model in the browser
19 — 4.1: Rolling your own Web ML models from a blank canvas
20 — 3.6.2: Using advanced pre-trained Web ML models - Part 2: Use MoveNet for pose estimation in browser
21 — 3.4: Tensors in Tensors out
22 — 4.2: Gathering, refining, and using data effectively for ML model datasets
23 — 4.3.2: How to train a neuron?
24 — 4.4.1: Implement a neuron for linear regression - Training data and outliers
25 — 4.3.1: What's a neuron?
26 — 4.4.3: Implement a neuron for linear regression - Model creation and training
27 — 4.5.1: Multi-layer perceptrons - The limits of a single neuron
28 — 4.5.2: Multi-layer perceptrons - Deep neural networks for non linear data
29 — 4.4.2: Implement a neuron for linear regression - Importing and normalizing training data
30 — 4.6.2: Multi-layer perceptrons for classification - Implementing a classifier in TensorFlow.js
31 — 4.6.1: Multi-layer perceptrons for classification
32 — 4.7.1: Beyond perceptrons: Convolutional Neural Network (CNNs) in the web browser
33 — 6.1: Using models from Python in the web browser with TensorFlow.js
34 — 6.4.1: Using a natural language model: Comment spam detection - setting up the web scaffolding
35 — 6.2: Converting Python saved models with the TensorFlow.js command line converter
36 — 6.3: Natural language processing (NLP) - understanding written text
37 — 5.1: Transfer learning: Retraining existing models in the web browser with TensorFlow.js
38 — 4.7.2: Beyond perceptrons: Convolutional Neural Network (CNNs) - Implementation with TensorFlow.js
39 — 5.2: Make your own Teachable Machine for image classification - transfer learning on the web in JS
40 — 5.3: Using layers models for transfer learning
41 — 6.4.2: Using a natural language model: Comment spam detection - loading a pretrained NLP model
42 — 6.4.3: Using a natural language model: Comment spam detection - word tokenization
43 — 6.5: Dealing with edge cases in spam detection
44 — 6.4.4: Using a natural language model: Comment spam detection - web sockets
45 — 6.6: Using a retrained spam detection model in the web browser with TensorFlow.js
46 — 7.1: Machine Learning as a Web Engineer - putting knowledge into practice
47 — 7.2: To the future and beyond - autoencoders, GANs, RNNs and more