Book Image

The TensorFlow Workshop

By : Matthew Moocarme, Abhranshu Bagchi, Anthony So, Anthony Maddalone
Book Image

The TensorFlow Workshop

By: Matthew Moocarme, Abhranshu Bagchi, Anthony So, Anthony Maddalone

Overview of this book

Getting to grips with tensors, deep learning, and neural networks can be intimidating and confusing for anyone, no matter their experience level. The breadth of information out there, often written at a very high level and aimed at advanced practitioners, can make getting started even more challenging. If this sounds familiar to you, The TensorFlow Workshop is here to help. Combining clear explanations, realistic examples, and plenty of hands-on practice, it’ll quickly get you up and running. You’ll start off with the basics – learning how to load data into TensorFlow, perform tensor operations, and utilize common optimizers and activation functions. As you progress, you’ll experiment with different TensorFlow development tools, including TensorBoard, TensorFlow Hub, and Google Colab, before moving on to solve regression and classification problems with sequential models. Building on this solid foundation, you’ll learn how to tune models and work with different types of neural network, getting hands-on with real-world deep learning applications such as text encoding, temperature forecasting, image augmentation, and audio processing. By the end of this deep learning book, you’ll have the skills, knowledge, and confidence to tackle your own ambitious deep learning projects with TensorFlow.

Related Content you might be interested in

Current Title:

Small book image
The TensorFlow Workshop
Matthew Moocarme | Abhranshu Bagchi | Anthony So | Anthony Maddalone
Dec, 2021 | 600 pages
Small book image
The Deep Learning Workshop
Anthony So | Mohan Kumar Silaparasetty | Nipun Sadvilkar | Thomas V Joseph | Mirza Rahim Baig
Jul, 2020 | 474 pages
Small book image
The Deep Learning with Keras Workshop
Matthew Moocarme | Ritesh Bhagwat | Mahla Abdolahnejad
Feb, 2020 | 446 pages
Small book image
The Deep Learning with Keras Workshop
Matthew Moocarme | Ritesh Bhagwat | Mahla Abdolahnejad
Jul, 2020 | 496 pages
Table of Contents (13 chapters)
Preface
About the Book
1
1. Introduction to Machine Learning with TensorFlow
1. Introduction to Machine Learning with TensorFlow
Introduction
Implementing Artificial Neural Networks in TensorFlow
The TensorFlow Library in Python
Introduction to Tensors
Tensor Addition
Reshaping
Tensor Multiplication
Optimization
Activation functions
Summary
Free Chapter
2
2. Loading and Processing Data
2. Loading and Processing Data
Introduction
Exploring Data Types
Data Preprocessing
Processing Tabular Data
Processing Image Data
Image Augmentation
Text Processing
Audio Processing
Summary
3
3. TensorFlow Development
3. TensorFlow Development
Introduction
TensorBoard
TensorFlow Hub
Google Colab
Summary
4
4. Regression and Classification Models
4. Regression and Classification Models
Introduction
Sequential Models
Model Fitting
Classification Models
Summary
5
5. Classification Models
5. Classification Models
Introduction
Binary Classification
Metrics for Classifiers
Multi-Class Classification
Multi-Label Classification
Summary
6
6. Regularization and Hyperparameter Tuning
6. Regularization and Hyperparameter Tuning
Introduction
Regularization Techniques
Hyperparameter Tuning
Summary
7
7. Convolutional Neural Networks
7. Convolutional Neural Networks
Introduction
CNNs
Image Representation
The Convolutional Layer
Pooling Layer
Image Augmentation
Binary Image Classification
Object Classification
Summary
8
8. Pre-Trained Networks
8. Pre-Trained Networks
Introduction
ImageNet
Transfer Learning
Fine-Tuning
TensorFlow Hub
Feature Extraction
Summary
9
9. Recurrent Neural Networks
9. Recurrent Neural Networks
Introduction
Sequential Data
Recurrent Neural Networks
Natural Language Processing
Back Propagation Through Time (BPTT)
Summary
10
10. Custom TensorFlow Components
10. Custom TensorFlow Components
Introduction
TensorFlow APIs
Implementing Custom Loss Functions
Implementing Custom Layers
Summary
11
11. Generative Models
11. Generative Models
Introduction
Text Generation
Generative Adversarial Networks
Deep Convolutional Generative Adversarial Networks (DCGANs)
Summary
Appendix
1. Introduction to Machine Learning with TensorFlow
2. Loading and Processing Data
3. TensorFlow Development
4. Regression and Classification Models
5. Classification Models
6. Regularization and Hyperparameter Tuning
7. Convolutional Neural Networks
8. Pre-Trained Networks
9. Recurrent Neural Networks
10. Custom TensorFlow Components
11. Generative Models

Back Propagation Through Time (BPTT)

There are many types of sequential models. You've already used simple RNNs, deep RNNs, and LSTMs. Let's take a look at a couple of additional models used for NLP.

Remember that you trained feed-forward models by first making a forward pass through the network that goes from input to output. This is the standard feed-forward model where the layers are densely connected. To train this kind of model, you can backpropagate the gradients through the network, taking the derivative of the loss of each weight parameter in the network. Then, you can adjust the parameters to minimize the loss.

But in RNNs, as discussed earlier, your forward pass through the network also consists of going forward in time, updating the cell state based on the input and the previous state, and generating an output, Y. At that time step, computing a loss and then finally summing these losses from the individual time steps gets your total loss.

This means that...

Previous Section
End of Section 6
Next Section