Keras 2.x Projects

Book description

Demonstrate fundamentals of Deep Learning and neural network methodologies using Keras 2.x

Key Features

  • Experimental projects showcasing the implementation of high-performance deep learning models with Keras.
  • Use-cases across reinforcement learning, natural language processing, GANs and computer vision.
  • Build strong fundamentals of Keras in the area of deep learning and artificial intelligence.

Book Description

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.

What you will learn

  • Apply regression methods to your data and understand how the regression algorithm works
  • Understand the basic concepts of classification methods and how to implement them in the Keras environment
  • Import and organize data for neural network classification analysis
  • Learn about the role of rectified linear units in the Keras network architecture
  • Implement a recurrent neural network to classify the sentiment of sentences from movie reviews
  • Set the embedding layer and the tensor sizes of a network

Who this book is for

If you are a data scientist, machine learning engineer, deep learning practitioner or an AI engineer who wants to build speedy intelligent applications with minimal lines of codes, then this book is the best fit for you. Sound knowledge of machine learning and basic familiarity with Keras library would be useful.

Publisher resources

Download Example Code

Table of contents

  1. Title Page
  2. Copyright and Credits
    1. Keras 2.x Projects
  3. About Packt
    1. Why subscribe?
  4. Contributors
    1. About the author
    2. About the reviewer
    3. Packt is searching for authors like you
  5. Preface
    1. Who this book is for
    2. What this book covers
    3. To get the most out of this book
      1. Download the example code files
      2. Download the color images
      3. Conventions used
    4. Get in touch
      1. Reviews
  6. Getting Started with Keras
    1. Introduction to Keras
    2. Keras backend options
      1. TensorFlow
      2. Theano
      3. CNTK
    3. Installation
      1. Optional dependencies
      2. Installing the backend engine
      3. Keras installation and configuration
    4. Model fitting in Keras
      1. The Keras sequential model architecture
      2. Keras functional API model architecture
    5. Summary
  7. Modeling Real Estate Using Regression Analysis
    1. Defining a regression problem
      1. Basic regression concepts
      2. Different types of regression
    2. Creating a linear regression model
    3. Multiple linear regression concepts
    4. Neural networks for regression using Keras
      1. Exploratory analysis
      2. Data splitting
      3. Neural network Keras model
      4. Multiple linear regression model
    5. Summary
  8. Heart Disease Classification with Neural Networks
    1. Basics of classification problems
    2. Different types of classification
      1. Classification algorithms
        1. Naive Bayes algorithm
        2. Gaussian mixture models
        3. Discriminant analysis
        4. K-nearest neighbors
        5. Support vector machine
      2. Bayesian decision theory
        1. Bayes' theorem
    3. Pattern recognition using a Keras neural network
      1. Exploratory analysis
        1. Handling missing data in Python
        2. Data scaling
      2. Data visualization
      3. Keras binary classifier
    4. Summary
  9. Concrete Quality Prediction Using Deep Neural Networks
    1. Basic concepts of ANNs
      1. Architecture of ANNs
      2. Learning paradigms
        1. Supervised learning
        2. Unsupervised learning
        3. Semi-supervised learning
      3. Understanding the structure of neural networks
        1. Weights and biases
      4. Types of activation functions
        1. Unit step activation function
        2. Sigmoid
        3. Hyperbolic tangent
        4. Rectified linear unit
    2. Multilayer neural networks
    3. Implementing multilayer neural networks in Keras
      1. Exploratory analysis
        1. Data visualization
        2. Data scaling
    4. Building a Keras deep neural network model
    5. Improving the model performance by removing outliers
    6. Summary
  10. Fashion Article Recognition Using Convolutional Neural Networks
    1. Understanding computer vision concepts
    2. Convolutional neural networks
      1. Convolution layer
      2. Pooling layers
      3. Rectified linear units
      4. Fully connected layer
      5. Structure of a CNN
    3. Common CNN architecture
      1. LeNet-5
      2. AlexNet
      3. ResNet
      4. VGG Net
      5. GoogleNet
    4. Implementing a CNN for object recognition
      1. Exploratory analysis
        1. Data scaling
      2. Using Keras in the CNN model
      3. Exploring the model's results
    5. Summary
  11. Movie Reviews Sentiment Analysis Using Recurrent Neural Networks
    1. Sentiment analysis basic concepts
      1. Sentiment analysis techniques
      2. The next challenges for sentiment analysis
      3. Lexicon and semantics analysis
    2. Recurrent neural networks
      1. Fully recurrent neural networks
      2. Recursive neural networks
      3. Hopfield recurrent neural networks
      4. Elman neural networks
      5. Long short-term memory network
    3. Classifying sentiment in movie reviews using an RNN
      1. IMDB Movie reviews dataset
      2. Exploratory analysis
      3. Keras recurrent neural network model
      4. Exploring model results
    4. Summary
  12. Stock Volatility Forecasting Using Long Short-Term Memory
    1. The basics of forecasting
      1. Forecast horizon
      2. Forecasting methods
        1. Quantitative methods
        2. Qualitative methods
    2. Time series analysis
      1. The classical approach to time series
      2. Estimation of the trend component
      3. Estimating the seasonality component
    3. Time series models
      1. Autoregressive models
      2. Moving average models
      3. Autoregressive moving average model
      4. Autoregressive integrated moving average models
    4. Long short-term memory in Keras
    5. Implementing an LSTM to forecast stock volatility
      1. Exploratory analysis
      2. Data scaling
      3. Data splitting
      4. Keras LSTM model
    6. Summary
  13. Reconstruction of Handwritten Digit Images Using Autoencoders
    1. Basic concepts of image recognition
      1. Image digitization
      2. Image recognition
    2. Optical character recognition
      1. Approaches to the problem
    3. Generative neural networks
      1. The restricted Boltzmann machine
      2. Autoencoders
      3. Variational autoencoders
      4. The generative adversarial network
      5. The adversarial autoencoder
    4. The Keras autoencoders model
    5. Implementing autoencoder Keras layers to reconstruct handwritten digit images
      1. The MNIST dataset
      2. Min–max normalization
      3. Keras model architecture
      4. Exploring model results
    6. Summary
  14. Robot Control System Using Deep Reinforcement Learning
    1. Robot control overview
      1. Three laws of robotics
      2. Short robotics timeline
        1. First-generation robots
        2. Second-generation robots
        3. Third-generation robots
        4. Fourth-generation robots
      3. Automatic control
    2. The environment for controlling robot mobility
      1. OpenAI Gym
    3. Reinforcement learning basics
      1. Agent-environment interface
      2. Reinforcement learning algorithms
        1. Dynamic Programming
        2. Monte Carlo methods
        3. Temporal difference learning
    4. Keras DQNs
      1. Q-learning
      2. Deep Q-learning
      3. Keras-RL library
    5. DQN to control a robot's mobility
      1. OpenAI Gym installation and methods
      2. The CartPole system
      3. Q-learning solution
      4. Deep Q-learning solution
    6. Summary
  15. Reuters Newswire Topics Classifier in Keras
    1. Natural language processing
      1. NLP phases
        1. Morphology analysis
        2. Syntax analysis
        3. Semantic analysis
        4. Pragmatic analysis
      2. Automatic processing problems
      3. NLP applications
        1. Information retrieval
        2. Information extraction
        3. Question-answering
        4. Automatic summarization
        5. Automatic translation
        6. Sentiment analysis
      4. NLP methods
        1. Sentence splitting
        2. Tokenization
        3. Part-of-speech tagging
        4. Shallow parsing
        5. Named entity recognition
        6. Syntactic parsing
        7. Semantic role labeling
      5. Natural language processing tools
        1. The Natural Language Toolkit
        2. The Stanford NLP Group software
        3. Apache OpenNLP
        4. GATE
    2. The Natural Language Toolkit
      1. Getting started with the NLTK
        1. Corpora
        2. Brown corpus
      2. Word and sentence tokenize
      3. Part-of-speech tagger
      4. Stemming and lemmatization
        1. Stemming
        2. Lemmatization
    3. Implementing a DNN to label sentences
      1. Exploratory analysis
      2. Data preparation
      3. Keras deep neural network model
    4. Summary
  16. What is Next?
    1. Deep learning methods
      1. Deep feedforward network
      2. Convolutional neural networks
      3. Recurrent neural networks
      4. Long short-term memory
      5. Restricted Boltzmann machine
      6. Deep belief network
      7. Generative adversarial networks
    2. Automated machine learning
      1. Auto-Keras
      2. Google Cloud ML Engine
      3. Azure Machine Learning Studio
      4. Amazon Web Services
    3. Differentiable neural computer
    4. Genetic programming and evolutionary strategies
      1. Introducing the genetic algorithm
        1. The fitness function
        2. Selection
        3. Mutation
    5. Inverse reinforcement learning
    6. Summary
  17. Other Books You May Enjoy
    1. Leave a review - let other readers know what you think

Product information

  • Title: Keras 2.x Projects
  • Author(s): Giuseppe Ciaburro
  • Release date: December 2018
  • Publisher(s): Packt Publishing
  • ISBN: 9781789536645