Machine Learning and Deep Learning with JavaScript

Course Curriculum

Chapter 1: Hands-On Machine Learning using JavaScript

Lecture 1: The Course Overview

Lecture 2: Introduction to Machine Learning

Lecture 3: Tour of the JavaScript Machine Learning Landscape

Lecture 4: Setting Up Our Machine Learning Environment

Lecture 5: Understand Regression with Linear Regression

Lecture 6: Understanding How Linear Regression Works

Lecture 7: Predicting Salaries after College Using Linear Regression

Lecture 8: Understand Classification with Logistic Regression

Lecture 9: Classifying Clothes Using Logistic Regression

Lecture 10: Model Evaluation

Lecture 11: Better Measures than Accuracy

Lecture 12: Understanding the Results

Lecture 13: Improving the Models

Lecture 14: What are Support Vector Machines?

Lecture 15: Using SVM Kernels to Transform Problems

Lecture 16: Image Classifier Using SVM

Lecture 17: Making Better Decision with Decision Trees

Lecture 18: Combining Decision Trees to Make Better Predictions

Lecture 19: Predicting Customer Churn Using Random Forests

Lecture 20: Introduction and Advantage of Unsupervised Learning

Lecture 21: Grouping Unlabeled Data in Meaningful Ways Using K-means Clustering

Lecture 22: Using Principal Component Analysis to Speed-up Machine Learning Algorithms

Lecture 23: Analyzing Plant Species Using K-means Clustering

Lecture 24: Introduction to Neural Networks

Lecture 25: How a Neural Network Works

Lecture 26: Neural Networks in Tensorflow.js

Lecture 27: Multiclass Classification Using TensorFlow.js

Chapter 2: Hands-On Machine Learning with TensorFlow.js

Lecture 1: The Course Overview

Lecture 2: Introduction to Machine Learning

Lecture 3: Getting Started with TensorFlow.js Using a Simple Example to Predict Weight

Lecture 4: Setting Up Our Machine Learning Environment

Lecture 5: Types of Supervised Learning

Lecture 6: Applying Regression

Lecture 7: Predicting Salaries after College Using TensorFlow

Lecture 8: Applying Classification

Lecture 9: Predicting Mental Health Issues Using Logistic Regression

Lecture 10: Understanding Simple Neural Networks

Lecture 11: Concepts in Neural Network

Lecture 12: Working with Deep Neural Networks

Lecture 13: Image Classification Using Neural Networks

Lecture 14: Model Evaluation

Lecture 15: Better Measures than Accuracy

Lecture 16: Improving the Models

Lecture 17: Optimizing the Models

Lecture 18: Using High-Level Layers API to Construct Neural Networks

Lecture 19: Building Advanced Neural Networks with Layers Easily

Lecture 20: Detecting Digits Using Layers

Lecture 21: Building A Classifier Using Layers

Lecture 22: Importing a Keras Model into TensorFlow.js

Lecture 23: Saving and Loading TensorFlow Models

Lecture 24: Importing TensorFlow SavedModel into TensorFlow.js

Lecture 25: Playing PAC-MAN Using a Webcam

Chapter 3: Deep Learning Projects with JavaScript

Lecture 1: The Course Overview

Lecture 2: What Makes Deep Learning in JavaScript Special?

Lecture 3: Getting Started with TensorFlow.js

Lecture 4: Loading Pre-Trained CNN and LSTM Models

Lecture 5: Preparing a New Text for Sentiment Analysis

Lecture 6: Using Loaded Model for Real-Time Text Analysis

Lecture 7: Loading a Set of Pre-Trained CNN Models for Emotion Detection in Photos

Lecture 8: Preparing a New Image for Analysis

Lecture 9: Using Our Models for Photo Emotion Detection

Lecture 10: Loading a Pre-Trained CNN Model for Voice Emotion Detection

Lecture 11: Preparing a New Audio Sample for Analysis

Lecture 12: Using the Loaded CNN Model for Detecting Emotions in Speech

Lecture 13: Create a New Model Based on a Pre-Trained CNN Model

Lecture 14: Getting and Preparing a New Audio Sample for Training and Testing

Lecture 15: Training and Testing the New Model

Lecture 16: Getting and Preparing Audio Sample

Lecture 17: Building a CNN Model for Emotion Detection

Lecture 18: Training and Testing the Model

Lecture 19: Using Trained CNN Model on New Audio Samples