Book Image

Applied Deep Learning with Keras

By : Ritesh Bhagwat, Mahla Abdolahnejad, Matthew Moocarme
Book Image

Applied Deep Learning with Keras

By: Ritesh Bhagwat, Mahla Abdolahnejad, Matthew Moocarme

Overview of this book

Though designing neural networks is a sought-after skill, it is not easy to master. With Keras, you can apply complex machine learning algorithms with minimum code. Applied Deep Learning with Keras starts by taking you through the basics of machine learning and Python all the way to gaining an in-depth understanding of applying Keras to develop efficient deep learning solutions. To help you grasp the difference between machine and deep learning, the book guides you on how to build a logistic regression model, first with scikit-learn and then with Keras. You will delve into Keras and its many models by creating prediction models for various real-world scenarios, such as disease prediction and customer churning. You’ll gain knowledge on how to evaluate, optimize, and improve your models to achieve maximum information. Next, you’ll learn to evaluate your model by cross-validating it using Keras Wrapper and scikit-learn. Following this, you’ll proceed to understand how to apply L1, L2, and dropout regularization techniques to improve the accuracy of your model. To help maintain accuracy, you’ll get to grips with applying techniques including null accuracy, precision, and AUC-ROC score techniques for fine tuning your model. By the end of this book, you will have the skills you need to use Keras when building high-level deep neural networks.

Related Content you might be interested in

Current Title:

Small book image
Applied Deep Learning with Keras
Ritesh Bhagwat | Mahla Abdolahnejad | Matthew Moocarme
Apr, 2019 | 412 pages
Small book image
The TensorFlow Workshop
Matthew Moocarme | Anthony Maddalone | Anthony So
Dec, 2021 | 600 pages
Small book image
Data Science with Python
Mohamed Noordeen Alaudeen | Aaron England | Rohan Chopra
Jul, 2019 | 426 pages
Small book image
Mastering Predictive Analytics with scikit-learn and TensorFlow
Alvaro Fuentes
Sep, 2018 | 154 pages
Table of Contents (12 chapters)
Applied Deep Learning with Keras
Applied Deep Learning with Keras
Preface
Preface
Preface
Preface
Free Chapter
1
Introduction to Machine Learning with Keras
Introduction to Machine Learning with Keras
Introduction
Data Representation
Data Preprocessing
Machine Learning Libraries
scikit-learn
Keras
Model Training
Model Tuning
Summary
2
Machine Learning versus Deep Learning
Machine Learning versus Deep Learning
Introduction
Linear Transformations
Introduction to Keras
Summary
3
Deep Learning with Keras
Deep Learning with Keras
Introduction
Building Your First Neural Network
Model Evaluation
Summary
4
Evaluate Your Model with Cross-Validation using Keras Wrappers
Evaluate Your Model with Cross-Validation using Keras Wrappers
Introduction
Cross-Validation
Cross-Validation for Deep Learning Models
Model Selection with Cross-validation
Summary
5
Improving Model Accuracy
Improving Model Accuracy
Introduction
Regularization
L1 and L2 Regularization
Dropout Regularization
Other Regularization Methods
Hyperparameter Tuning with scikit-learn
Summary
6
Model Evaluation
Model Evaluation
Introduction
Accuracy
Imbalanced Datasets
Confusion Matrix
Summary
7
Computer Vision with Convolutional Neural Networks
Computer Vision with Convolutional Neural Networks
Introduction
Computer Vision
Convolutional Neural Networks
Architecture of a CNN
Image Augmentation
Summary
8
Transfer Learning and Pre-Trained Models
Transfer Learning and Pre-Trained Models
Introduction
Pre-Trained Sets and Transfer Learning
Fine-Tuning a Pre-Trained Network
Summary
9
Sequential Modeling with Recurrent Neural Networks
Sequential Modeling with Recurrent Neural Networks
Introduction
Sequential Memory and Sequential Modeling
Recurrent Neural Networks (RNNs)
Long Short-Term Memory (LSTM)
Summary

Introduction

Machine learning is the science of utilizing machines to emulate human tasks and to have the machine improve their performance of that task over time. By feeding machines data in the form of observations of real-world events, they can develop patterns and relationships that will optimize an objective function, such as the accuracy of a binary classification task or the error in a regression task. In general, the usefulness of machine learning is in the ability to learn highly complex and non-linear relationships in large datasets and to replicate the results of that learning many times.

Take, for example, the classification of a dataset of pictures of either dogs or cats into classes of their respective type. For a human, this is trivial, and the accuracy would likely be very high. However, it may take around a second to categorize each picture, and scaling the task can only be achieved by increasing the number of humans, which may be infeasible. While it may be difficult, though certainly not impossible, for machines to reach the same level of accuracy as humans for this task, machines can classify many images per second, and scaling can be easily done by increasing the processing power of single machine, or making the algorithm more efficient.

Figure 1.1: A trivial classification task for humans, but quite difficult for machines

While the trivial task of classifying dogs and cats may be simple for us humans, the same principles that are used to create a machine learning model classify dogs and cats can be applied to other classification tasks that humans may struggle with. An example of this is identifying tumors in Magnetic Resonance Images (MRIs). For humans, this task requires a medical professional with years of experience, whereas a machine may only need a dataset of labeled images.

Figure 1.2: A non-trivial classification task for humans. Are you able to spot the tumors?

Previous Section
End of Section 2
Next Section