Book Image

The Deep Learning with Keras Workshop

By : Matthew Moocarme, Mahla Abdolahnejad, Ritesh Bhagwat
1 (1)
Book Image

The Deep Learning with Keras Workshop

1 (1)
By: Matthew Moocarme, Mahla Abdolahnejad, Ritesh Bhagwat

Overview of this book

New experiences can be intimidating, but not this one! This beginner’s guide to deep learning is here to help you explore deep learning from scratch with Keras, and be on your way to training your first ever neural networks. What sets Keras apart from other deep learning frameworks is its simplicity. With over two hundred thousand users, Keras has a stronger adoption in industry and the research community than any other deep learning framework. The Deep Learning with Keras Workshop starts by introducing you to the fundamental concepts of machine learning using the scikit-learn package. After learning how to perform the linear transformations that are necessary for building neural networks, you'll build your first neural network with the Keras library. As you advance, you'll learn how to build multi-layer neural networks and recognize when your model is underfitting or overfitting to the training data. With the help of practical exercises, you’ll learn to use cross-validation techniques to evaluate your models and then choose the optimal hyperparameters to fine-tune their performance. Finally, you’ll explore recurrent neural networks and learn how to train them to predict values in sequential data. By the end of this book, you'll have developed the skills you need to confidently train your own neural network models.

Related Content you might be interested in

Current Title:

Small book image
The Deep Learning with Keras Workshop
Matthew Moocarme | Mahla Abdolahnejad | Ritesh Bhagwat
Jul, 2020 | 496 pages
Small book image
The TensorFlow Workshop
Matthew Moocarme | Anthony Maddalone | Anthony So
Dec, 2021 | 600 pages
Small book image
Mastering Predictive Analytics with scikit-learn and TensorFlow
Alvaro Fuentes
Sep, 2018 | 154 pages
Small book image
Machine Learning for Healthcare Analytics Projects
Eduonix Learning Solutions
Oct, 2018 | 134 pages
Table of Contents (11 chapters)
Preface
About the Book
1
1. Introduction to Machine Learning with Keras
1. Introduction to Machine Learning with Keras
Introduction
Data Representation
Data Preprocessing
Life Cycle of Model Creation
scikit-learn
Keras
Model Training
Model Tuning
Summary
Free Chapter
2
2. Machine Learning versus Deep Learning
2. Machine Learning versus Deep Learning
Introduction
Linear Transformations
Introduction to Keras
Summary
3
3. Deep Learning with Keras
3. Deep Learning with Keras
Introduction
Building Your First Neural Network
Model Evaluation
Summary
4
4. Evaluating Your Model with Cross-Validation Using Keras Wrappers
4. Evaluating Your Model with Cross-Validation Using Keras Wrappers
Introduction
Cross-Validation
Cross-Validation for Deep Learning Models
Model Selection with Cross-Validation
Summary
5
5. Improving Model Accuracy
5. Improving Model Accuracy
Introduction
Regularization
L1 and L2 Regularization
Dropout Regularization
Other Regularization Methods
Hyperparameter Tuning with scikit-learn
Summary
6
6. Model Evaluation
6. Model Evaluation
Introduction
Accuracy
Imbalanced Datasets
Confusion Matrix
Summary
7
7. Computer Vision with Convolutional Neural Networks
7. Computer Vision with Convolutional Neural Networks
Introduction
Computer Vision
Convolutional Neural Networks
The Architecture of a CNN
Image Augmentation
Summary
8
8. Transfer Learning and Pre-Trained Models
8. Transfer Learning and Pre-Trained Models
Introduction
Pre-Trained Sets and Transfer Learning
Fine-Tuning a Pre-Trained Network
Summary
9
9. Sequential Modeling with Recurrent Neural Networks
9. Sequential Modeling with Recurrent Neural Networks
Introduction
Sequential Memory and Sequential Modeling
Recurrent Neural Networks (RNNs)
Long Short-Term Memory (LSTM)
Summary
Appendix
1. Introduction to Machine Learning with Keras
2. Machine Learning versus Deep Learning
3. Deep Learning with Keras
4. Evaluating Your Model with Cross-Validation Using Keras Wrappers
5. Improving Model Accuracy
6. Model Evaluation
7. Computer Vision with Convolutional Neural Networks
8. Transfer Learning and Pre-Trained Models
9. Sequential Modeling with Recurrent Neural Networks

Long Short-Term Memory (LSTM)

LSTMs are RNNs whose main objective is to overcome the shortcomings of the vanishing gradient and exploding gradient problems. The architecture is built so that they remember data and information for a long period of time.

LSTMs were designed to overcome the limitation of the vanishing and exploding gradient problems. LSTM networks are a special kind of RNN that are capable of learning long-term dependencies. They are designed to avoid the long-term dependency problem; being able to remember information for long intervals of time is how they are wired. The following diagram displays a standard recurrent network where the repeating module has a tanh activation function. This is a simple RNN. In this architecture, we often have to face the vanishing gradient problem:

Figure 9.12: A simple RNN model

The LSTM architecture is similar to simple RNNs, but their repeating module has different components, as shown in the following diagram...

Previous Section
End of Section 5
Next Section