Beginning Application Development with TensorFlow and Keras

Table of contents

1. Chapter 1 : Introduction to Neural Networks and Deep Learning
   1. Course Overview 00:04:02
   2. Setting up your Environment 00:05:06
   3. Lesson Overview 00:01:36
   4. What are Neural Networks and Deep Learning? 00:06:37
   5. Limitations of Deep Learning 00:05:05
   6. Common Components and Operations of Neural Networks 00:06:04
   7. Configuring a Deep Learning Environment 00:01:23
   8. Installing Python 3 00:05:29
   9. Installing TensorFlow, Keras and TensorBoard 00:09:36
   10. Installing Jupyter, Notebooks, Pandas and NumPy 00:03:15
   11. Installation Completion 00:04:16
   12. Training a Neural Network with TensorFlow convolutional layer 00:05:07
   13. Training a Neural Network with TensorFlow fully connected layer 00:02:43
   14. Train a Neural Network with TensorFlow 00:06:07
   15. Testing network performance with unseen data 00:03:51
   16. Summary 00:01:23
2. Chapter 2 : Model Architecture
   1. Lesson Overview 00:01:04
   2. Choosing the Right Model Architecture 00:08:39
   3. Data Normalization 00:05:25
   4. Using Keras as a TensorFlow Interface 00:02:38
   5. Designing a Model 00:05:11
   6. Training a Model 00:03:57
   7. Making Predictions 00:02:24
   8. The Keras Paradigm 00:02:10
   9. From Data Preparation to Modeling 00:05:34
   10. Reshaping the Time-Series Data 00:09:20
   11. Reshaping the Time-Series Data 00:03:52
   12. Training a Model 00:02:53
   13. Training a Model 00:01:17
   14. Making Predictions 00:01:53
   15. Overfitting 00:01:01
   16. Summary 00:00:44
3. Chapter 3 : Model Evaluation and Optimization
   1. Lesson Overview 00:01:13
   2. Model Evaluation 00:10:15
   3. Using TensorBoard 00:08:58
   4. Implementing Model Evaluation Metrics 00:07:24
   5. Evaluating Bitcoin Model 00:14:19
   6. Model Predictions 00:11:55
   7. Interpreting Predictions 00:05:47
   8. Hyperparameter Optimization 00:09:49
   9. Epochs Implementation 00:10:50
   10. Regularization Strategies Implementation 00:06:48
   11. Summary 00:01:27
4. Chapter 4 : Productization
   1. Lesson Overview 00:01:34
   2. Handling and Dealing with New Data 00:12:15
   3. Re-Training an Old Model 00:12:46
   4. Training a New Model 00:03:33
   5. Deploying a Model as a Web Application 00:04:20
   6. Building and executing a Docker run command 00:03:49
   7. Deployment and using Cryptonic 00:08:59
   8. Summary 00:01:38