by Jakub Konczyk | Released December 2018 | ISBN: 9781789950908

Learn how to do text sentiment analysis and detect emotions in people's portraits and their voices using TensorFlow.jsAbout This VideoGet started with Deep Learning quickly using JavaScript tools already at your fingertipsSolve one of the most useful Machine Learning problems in a wide range of data types using a variety of Deep Learning methodsQuickly get results using pre-trained models and train your own custom Deep Learning models from scratchIn DetailGetting started with Deep Learning seems overwhelming with so many options to choose from, so you might be wondering where to start, which tools to choose, and how to actually set them up? The good news is that you already have the key tool in front of you: your web browser with a powerful JavaScript engine inside it. And when you add the TensorFlow.js library to this combo, you can use Deep Learning methods via JavaScript in no time.In this course, you will through the process of getting started with TensorFlow.js to detect emotions with a lot of different types of data. You will start by learning how to build a deep learning tool to judge whether a piece of text is positive or negative. Since you will want tangible results quickly, you will use a pre-trained model to do that and include it into your own web application. You will move on to learn how to detect human emotions based only on pictures and voices using pre-trained models as well. Towards the end, you will learn how to modify a pre-trained model to train the emotional detector from scratch using your own data.By the end of this course you will know how to use Deep Learning models and train your own models from the ground up using JavaScript and the TensorFlow.js library.The code bundle for this video course is available at - https://github.com/PacktPublishing/Deep-Learning-Projects-with-JavaScriptDownloading the example code for this course: You can download the example code files for all Packt video courses you have purchased from your account at http://www.PacktPub.com. If you purchased this course elsewhere, you can visit http://www.PacktPub.com/support and register to have the files e-mailed directly to you. Show and hide more

1. Chapter 1 : Easy to Use Deep Learning Tools at Your Fingertips
   • The Course Overview 00:06:49
   • What Makes Deep Learning in JavaScript Special? 00:02:39
   • Getting Started with TensorFlow.js 00:05:57
2. Chapter 2 : Text Sentiment Analysis
   • Loading Pre-Trained CNN and LSTM Models 00:07:24
   • Preparing a New Text for Sentiment Analysis 00:07:58
   • Using Loaded Model for Real-Time Text Analysis 00:10:09
3. Chapter 3 : What You See Is What You Get – Photo Emotion Detection
   • Loading a Set of Pre-Trained CNN Models for Emotion Detection in Photos 00:09:14
   • Preparing a New Image for Analysis 00:06:52
   • Using Our Models for Photo Emotion Detection 00:03:57
4. Chapter 4 : You Sound Happy – Speech Emotion Detection
   • Loading a Pre-Trained CNN Model for Voice Emotion Detection 00:03:34
   • Preparing a New Audio Sample for Analysis 00:11:16
   • Using the Loaded CNN Model for Detecting Emotions in Speech 00:04:02
5. Chapter 5 : Improving Speech Emotion Detection Using Transfer Learning
   • Create a New Model Based on a Pre-Trained CNN Model 00:05:52
   • Getting and Preparing a New Audio Sample for Training and Testing 00:05:27
   • Training and Testing the New Model 00:09:28
6. Chapter 6 : Training Speech Emotion Detection Model From Scratch
   • Getting and Preparing Audio Sample 00:09:44
   • Building a CNN Model for Emotion Detection 00:08:42
   • Training and Testing the Model 00:09:11
   • Using Trained CNN Model on New Audio Samples 00:05:00
Show and hide more