Packt+ | Advance your knowledge in tech

0

All Products

Best Sellers

New Releases

Books

Videos

Audiobooks

Free Learning

Applied Deep Learning with Keras

You're reading from Applied Deep Learning with Keras Solve complex real-life problems with the simplicity of Keras

Product type Paperback

Published in Apr 2019

Publisher

ISBN-13 9781838555078

Length 412 pages

Edition 1st Edition

Languages

Python

Tools

Keras

Concepts

Deep Learning

Authors (3):

Ritesh Bhagwat

Mahla Abdolahnejad

Matthew Moocarme

View More author details

Table of Contents (21) Chapters

About the Book

About the Authors

Learning Objectives

Audience

Approach

Hardware Requirements

Software Requirements

Conventions

Installation and Setup

Installing the Code Bundle

Additional Resources

1. Introduction to Machine Learning with Keras FREE CHAPTER

2. Machine Learning versus Deep Learning

3. Deep Learning with Keras

4. Evaluate 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

1. Appendix

Regularization

Since deep neural networks are highly flexible models, overfitting is an issue that can often arise when training them. Therefore, one very important part of becoming a deep learning expert is knowing how to detect overfitting, and subsequently how to address the overfitting problem in your model. Regularization techniques are an important group of methods specifically aimed at reducing overfitting in machine learning models. Understanding regularization techniques thoroughly and being able to apply them to your deep neural networks is an essential step toward building deep neural networks in order to solve real-life problems. In this section, you will learn about the underlying concepts of regularization, providing you with the foundation required for the following sections, where you will learn how to implement various types of regularization methods using Keras.

The Need for Regularization

The main goal of machine learning is to build models that perform well on not only...

The rest of the chapter is locked

Register for a free Packt account to unlock a world of extra content!

A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.

Unlock this book and the full library FREE for 7 days

Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of

Start free trial

Renews at $15.99/month. Cancel anytime

Authors (3)

Ritesh Bhagwat

Ritesh Bhagwat

Ritesh Bhagwat has a master's degree in applied mathematics with a specialization in computer science. He has over 14 years of experience in data-driven technologies and has led and been a part of complex projects ranging from data warehousing and business intelligence to machine learning and artificial intelligence. He has worked with top-tier global consulting firms as well as large multinational financial institutions. Currently, he works as a data scientist. Besides work, he enjoys playing and watching cricket and loves to travel. He is also deeply interested in Bayesian statistics.

See other products by Ritesh Bhagwat

Mahla Abdolahnejad

Mahla Abdolahnejad

Mahla Abdolahnejad is a Ph.D. candidate in systems and computer engineering with Carleton University, Canada. She also holds a bachelor's degree and a master's degree in biomedical engineering, which first exposed her to the field of artificial intelligence and artificial neural networks, in particular. Her Ph.D. research is focused on deep unsupervised learning for computer vision applications. She is particularly interested in exploring the differences between a human's way of learning from the visual world and a machine's way of learning from the visual world, and how to push machine learning algorithms toward learning and thinking like humans.

See other products by Mahla Abdolahnejad

Matthew Moocarme

Matthew Moocarme

Matthew Moocarme is an accomplished data scientist with more than eight years of experience in creating and utilizing machine learning models. He comes from a background in the physical sciences, in which he holds a Ph.D. in physics from the Graduate Center of CUNY. Currently, he leads a team of data scientists and engineers in the media and advertising space to build and integrate machine learning models for a variety of applications. In his spare time, Matthew enjoys sharing his knowledge with the data science community through published works, conference presentations, and workshops.

See other products by Matthew Moocarme

Other recommended products

Related to this chapter

The Deep Learning with Keras Workshop

The Deep Learning with Keras Workshop

Cut through the noise and get real results with a step-by-step approach to understanding deep learning with Keras programming

Feb 2020 14h 52m

Mastering Predictive Analytics with scikit-learn and TensorFlow

Mastering Predictive Analytics with scikit-learn and TensorFlow

In this book, you will find a range of methods to improve the performance of almost any predictive model, from ensemble methods to dimensionality reduction and cross-validation. You will learn the tools to produce advanced predictive models. In addition, you will dive into the exiting field of Deep Learning using TensorFlow.

Machine Learning for Healthcare Analytics Projects

Machine Learning for Healthcare Analytics Projects

Machine Learning in the healthcare domain is booming because of its abilities to provide accurate and stabilized techniques. This book is packed with new methodologies to create efficient solutions for healthcare analytics. We will build five end-to-end projects to evaluate the efficiency of AI apps to carry out simple-to-complex healthcare analytics tasks.

Oct 2018 4h 28m

Python Deep Learning Cookbook

Python Deep Learning Cookbook

Deep Learning is a rapidly evolving field of Machine Learning science which gives machines the ability to learn from information. This book contains detailed recipes to tackle with the common and not so common problems while dealing with deep learning algorithms and models in Python. You will benefit from this book by finding technical solutions to the issues presented, along with a detailed explanation of the solutions, and a discussion on corresponding pros and cons of implementing the proposed solution using Theano, Tensorflow, MXNet, and Keras. You'll come across recipes on data pre-processing, network models and topologies, supervised and unsupervised learning presented in a “solution to problem” fashion.

Oct 2017 11h 0m

Neural Network Projects with Python

Neural Network Projects with Python

This book contains practical implementations of several deep learning projects in multiple domains, including in regression-based tasks such as taxi fare prediction in New York City, image classification of cats and dogs using a convolutional neural network, implementing a facial recognition security system using Siamese Neural Networks, and more.

Feb 2019 10h 16m

Keras Deep Learning Cookbook

Keras Deep Learning Cookbook

This book gives you a practical, hands-on understanding of how you can leverage the power of Python and Keras to perform effective deep learning. It presents a unique problem-solution approach to tackle various problems in training different types of neural networks while taking care of the speed and accuracy of these models

Oct 2018 8h 24m

scikit-learn Cookbook

scikit-learn Cookbook

scikit-learn has evolved as a robust library for machine learning applications in python with support for a wide range of supervised and unsupervised learning algorithms. This edition brings to you the various enhancements to its model implementations, API and bug fixes in the latest major release of scikit-learn to support Python. This book covers easy to follow recipes right from mathematical operations to implementing various supervised, unsupervised and deep learning algorithms with scikit-learn. Get practical hands-on knowledge to implement various models and algorithms like Multi-Layer Perceptrons, time-series split, MAE criterion for regression, criteria for gradient boosting, Classifier, Regressor, and much more.

Nov 2017 12h 28m

Neural Networks with Keras Cookbook

Neural Networks with Keras Cookbook

This book presents solutions to the majority of the challenges you will face while training neural networks to solve deep learning problems. It covers the trending deep learning architectures used in industry and tackles a variety of use cases in computer vision, text processing, audio analysis, recommender systems, and game bots

Feb 2019 18h 56m

Advanced Deep Learning with R

Advanced Deep Learning with R

This book will help readers to apply deep learning algorithms in R using advanced examples. You will cover variants of neural network models such as ANN, CNN, RNN, LSTM, and more using expert techniques. Readers will make use of popular deep learning libraries such as Keras-R, Tensorflow-R, and more to implement AI models.

Dec 2019 11h 44m

Machine Learning with scikit-learn Quick Start Guide

Machine Learning with scikit-learn Quick Start Guide

Scikit-learn is a robust machine learning library for the Python programming language. It provides a set of supervised and unsupervised learning algorithms. This book is the easiest way to learn how to deploy, optimize and evaluate all the important machine learning algorithms that scikit-learn provides.

Oct 2018 5h 44m

Master Data Science with Python

Master Data Science with Python

Data Science with Python will help you get comfortable with using the Python environment for data science. You will learn all the libraries that a data scientist uses on a daily basis. By the end of this course, you will be able to take a large raw dataset, clean it, manipulate it, and run machine learning algorithms to obtain results that influence business decisions.

Jul 2019 14h 12m

Hands-On Gradient Boosting with XGBoost and scikit-learn

Hands-On Gradient Boosting with XGBoost and scikit-learn

This practical XGBoost guide will put your Python and scikit-learn knowledge to work by showing you how to build powerful, fine-tuned XGBoost models with impressive speed and accuracy. This book will help you to apply XGBoost's alternative base learners, use unique transformers for model deployment, discover tips from Kaggle masters, and much more!

Oct 2020 10h 20m

Personalised recommendations for you

Based on your interests and search pattern

Mathematics of Machine Learning

Mathematics of Machine Learning

Deepen your theoretical knowledge and enhance your ability to solve complex machine learning problems with structured guidance. Gain the confidence to engage with advanced ML literature and tailor algorithms to meet your project requirements.

May 2025 24h 20m

Generative AI with Python and PyTorch

Generative AI with Python and PyTorch

Learn how to create images and text using VAEs, GANs, LSTMs, and transformers. Implement applications in natural language processing and computer vision through practical tutorials.

Mar 2025 15h 0m

Practical Generative AI with ChatGPT

Practical Generative AI with ChatGPT

This book helps you unlock ChatGPT's potential to make your working life better. From prompt engineering to creating custom GPTs, you'll enhance your productivity, creativity, and efficiency with practical insights and advanced techniques.

Apr 2025 12h 52m

Generative AI with LangChain

Generative AI with LangChain

Gain a solid foundation in LangChain, agentic AI, and LangGraph, and learn to build production-ready systems with multi-agent architectures, advanced RAG pipelines, Tree of Thought reasoning, agent handoffs, and fine-grained error handling.

May 2025 15h 52m

Architecting Power BI Solutions in Microsoft Fabric

Architecting Power BI Solutions in Microsoft Fabric

Power BI provides several options to solve common data problems, and designing the correct solution for each scenario can be a daunting task. This book makes it easier by guiding you through designing optimal solutions using Power BI.

Apr 2025 14h 16m

Microsoft Identity and Access Administrator SC-300 Exam Guide

Microsoft Identity and Access Administrator SC-300 Exam Guide

This comprehensive guide covers key topics such as Microsoft Entra ID implementation, authentication and access management, external user management, and hybrid identity solutions, providing practical insights and techniques for SC-300 exam success.

Mar 2025 19h 48m

LLM Design Patterns

LLM Design Patterns

This book helps you gain practical skills to develop and deploy LLMs. You'll learn data prep, training, pruning, quantization, and evaluation, as well as explore RAG, advanced prompting, and optimization to build robust, scalable language models.

May 2025 17h 48m

Tableau Cookbook for Experienced Professionals

Tableau Cookbook for Experienced Professionals

Advance your Tableau knowledge beyond the basics, streamline dashboard performance, tackle advanced geospatial challenges, and unlock API potential while fortifying your corporate data infrastructure with proven best practices.

Apr 2025 12h 24m

Time Series Analysis with Spark

Time Series Analysis with Spark

This book offers a complete guide to time series analysis with Apache Spark and Databricks, covering essential concepts and advanced techniques including Generative AI to equip readers with skills for real-world challenges across industries.

Mar 2025 9h 56m

Hands-On Artificial Intelligence for IoT

Hands-On Artificial Intelligence for IoT

Transform IoT systems with the power of artificial intelligence using this hands-on guide. Dive into practical techniques and expert insights to innovate and optimize your IoT devices, making them smarter and more efficient.

May 2025 15h 44m