Book Image

Keras 2.x Projects

By : Giuseppe Ciaburro

Book Image

Keras 2.x Projects

By: Giuseppe Ciaburro

Overview of this book

Keras 2.x Projects explains how to leverage the power of Keras to build and train state-of-the-art deep learning models through a series of practical projects that look at a range of real-world application areas. To begin with, you will quickly set up a deep learning environment by installing the Keras library. Through each of the projects, you will explore and learn the advanced concepts of deep learning and will learn how to compute and run your deep learning models using the advanced offerings of Keras. You will train fully-connected multilayer networks, convolutional neural networks, recurrent neural networks, autoencoders and generative adversarial networks using real-world training datasets. The projects you will undertake are all based on real-world scenarios of all complexity levels, covering topics such as language recognition, stock volatility, energy consumption prediction, faster object classification for self-driving vehicles, and more. By the end of this book, you will be well versed with deep learning and its implementation with Keras. You will have all the knowledge you need to train your own deep learning models to solve different kinds of problems.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Getting Started with Keras

Getting Started with Keras

Introduction to Keras

Keras backend options

Model fitting in Keras

Modeling Real Estate Using Regression Analysis

Modeling Real Estate Using Regression Analysis

Defining a regression problem

Creating a linear regression model

Multiple linear regression concepts

Neural networks for regression using Keras

Heart Disease Classification with Neural Networks

Heart Disease Classification with Neural Networks

Basics of classification problems

Different types of classification

Pattern recognition using a Keras neural network

Concrete Quality Prediction Using Deep Neural Networks

Concrete Quality Prediction Using Deep Neural Networks

Basic concepts of ANNs

Multilayer neural networks

Implementing multilayer neural networks in Keras

Building a Keras deep neural network model

Improving the model performance by removing outliers

Fashion Article Recognition Using Convolutional Neural Networks

Fashion Article Recognition Using Convolutional Neural Networks

Understanding computer vision concepts

Convolutional neural networks

Common CNN architecture

Implementing a CNN for object recognition

Movie Reviews Sentiment Analysis Using Recurrent Neural Networks

Movie Reviews Sentiment Analysis Using Recurrent Neural Networks

Sentiment analysis basic concepts

Recurrent neural networks

Classifying sentiment in movie reviews using an RNN

Stock Volatility Forecasting Using Long Short-Term Memory

Stock Volatility Forecasting Using Long Short-Term Memory

The basics of forecasting

Time series analysis

Time series models

Long short-term memory in Keras

Implementing an LSTM to forecast stock volatility

Reconstruction of Handwritten Digit Images Using Autoencoders

Reconstruction of Handwritten Digit Images Using Autoencoders

Basic concepts of image recognition

Optical character recognition

Generative neural networks

The Keras autoencoders model

Implementing autoencoder Keras layers to reconstruct handwritten digit images

Robot Control System Using Deep Reinforcement Learning

Robot Control System Using Deep Reinforcement Learning

Robot control overview

The environment for controlling robot mobility

Reinforcement learning basics

DQN to control a robot's mobility

Reuters Newswire Topics Classifier in Keras

Reuters Newswire Topics Classifier in Keras

Natural language processing

The Natural Language Toolkit

Implementing a DNN to label sentences

What is Next?

Deep learning methods

Automated machine learning

Differentiable neural computer

Genetic programming and evolutionary strategies

Inverse reinforcement learning

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Improving the model performance by removing outliers

In the Data visualization section, we saw that some predictors have outliers. Outliers are the values that, when compared to others, are particularly extreme. Outliers are a problem because they tend to distort data analysis results, in particular, in descriptive statistics and correlations. Outliers have a large influence on the fit, because squaring the residuals magnifies the effects of these extreme data points. For these reasons, it may be necessary to remove these values first to improve the performance of the model.

In some cases, you may be tempted to remove outliers that are influential or have an excessive impact on the synthesis measures you want to consider (such as the mean or the linear correlation coefficient). However, this way of proceeding isn't always cautious, unless the reasons for an abnormal observation...