by Radhika Datar | Released January 2019 | ISBN: 9781788999380

Implementing deep learning algorithms with PythonAbout This VideoApply Deep Learning techniques to develop solutions for a healthcare datasetA hands-on guide covering common as well as not-so-common problems in deep learning using PythonGet started with Deep Learning and build complex models layer by layer, with increasing complexity, in no time.In DetailDeep learning is the next step to a more advanced implementation of machine learning. The course resolves the confusion between machine learning and deep learning by focusing only on deep learning concepts. Deep learning techniques are used in real-world scenarios such as image scanning, face detection, and many more. It is important to know deep learning algorithms as they are currently trending in sectors such as healthcare, finance, and many more. This hands-on course will help you tackle various issues that you come across while building your Deep Learning applications in the healthcare domain. Right from building your neural nets to reinforcement learning and working with different Deep Learning applications such as computer Vision and voice and image recognition, this course will be your guide in tackling different situations and issues and provide the end to end application of deep learning concepts in the healthcare domain. By the end of the course, you will be able to build neural networks and Deep learning models for your own projects.The code bundle for this video course is available at - https://github.com/PacktPublishing/Hands-On-Python-Deep-LearningDownloading 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 : Building and Evaluating a Basic Neural Network
   • Course Overview 00:02:17
   • Introduction to Deep Learning and Neural Networks 00:12:01
   • Building Neural Network 00:08:15
   • Evaluating the Neural Network 00:08:08
2. Chapter 2 : Feature Exploration
   • Ohio Clinic Data Set 00:01:43
   • Analyze and Explore Your Data 00:10:10
   • Feature Exploration of Our Dataset 00:07:07
   • Performing Data Analysis 00:07:26
3. Chapter 3 : Building an Image Recognition Module
   • Introduction to Image Recognition 00:01:26
   • Environmental Setup 00:05:44
   • Using Spyder IDE 00:08:47
   • Encode the Image 00:06:45
   • Understanding Testing Functionality and Output 00:07:02
4. Chapter 4 : Building a Face Recognition Module
   • Introduction to Face Recognition 00:02:00
   • Problem Statement 00:01:29
   • Face Recognition File and Output 00:11:41
5. Chapter 5 : Improving the Performance with Keras
   • Introduction to Keras 00:01:25
   • Feedforward Neural Network 00:03:00
   • Representing Simple FeedForward Neural Network Using Keras 00:05:58
   • Scaling Input Images 00:06:16
6. Chapter 6 : Document Characterization
   • Introduction to LSTM 00:01:41
   • LSTM Architecture 00:01:45
   • How LSTM Network Works 00:05:54
   • Fitting Neural Network and Output 00:04:33
7. Chapter 7 : Text Summarization with Deep Learning
   • Introduction to Text Summarization 00:01:30
   • Understanding the Problem Statement 00:02:45
   • Training and Testing Data 00:03:47
   • Preparation Data 00:04:11
8. Chapter 8 : Dialog Generation with Deep Learning
   • Introduction to Encode-Decode Model 00:02:13
   • Implementing Decoder and Encoder 00:05:12
   • Defining the Module and Output 00:05:22
Show and hide more