Description 
1 online resource (412 p.) 
Contents 
Cover; FM; Copyright; Table of Contents; Preface; Chapter 1: Introduction to Machine Learning with Keras; Introduction; Data Representation; Tables of Data; Loading Data; Exercise 1: Loading a Dataset from the UCI Machine Learning Repository; Data Preprocessing; Exercise 2: Cleaning the Data; Appropriate Representation of the Data; Exercise 3: Appropriate Representation of the Data; Life Cycle of Model Creation; Machine Learning Libraries; scikitlearn; Keras; Advantages of Keras; Disadvantages of Keras; More than Building Models; Model Training; Classifiers and Regression Models 

Classification TasksRegression Tasks; Training and Test Datasets; Model Evaluation Metrics; Exercise 4: Creating a Simple Model; Model Tuning; Baseline Models; Exercise 5: Determining a Baseline Model; Regularization; CrossValidation; Activity 1: Adding Regularization to the Model; Summary; Chapter 2: Machine Learning versus Deep Learning; Introduction; Advantages of ANNs over Traditional Machine Learning Algorithms; Advantages of Traditional Machine Learning Algorithms over ANNs; Hierarchical Data Representation; Linear Transformations; Scalars, Vectors, Matrices, and Tensors 

CrossValidationDrawbacks of Splitting a Dataset Only Once; KFold CrossValidation; LeaveOneOut CrossValidation; Comparing the KFold and LOO Methods; CrossValidation for Deep Learning Models; Keras Wrapper with scikitlearn; Exercise 11: Building the Keras Wrapper with scikitlearn for a Regression Problem; CrossValidation with scikitlearn; CrossValidation Iterators in scikitlearn; Exercise 12: Evaluate Deep Neural Networks with CrossValidation; Activity 5: Model Evaluation Using CrossValidation for a Diabetes Diagnosis Classifier; Model Selection with Crossvalidation 

Forward Propagation for Making PredictionsLoss Function; Backpropagation for Computing Derivatives of Loss Function; Gradient Descent for Learning Parameters; Exercise 10: Neural Network Implementation with Keras; Activity 3: Building a SingleLayer Neural Network for Performing Binary Classification; Model Evaluation; Evaluating a Trained Model with Keras; Splitting Data into Training and Test Sets; Underfitting and Overfitting; Early Stopping; Activity 4: Diabetes Diagnosis with Neural Networks; Summary; Chapter 4: Evaluate Your Model with CrossValidation using Keras Wrappers; Introduction 

Tensor AdditionExercise 6: Perform Various Operations with Vectors, Matrices, and Tensors; Reshaping; Matrix Transposition; Exercise 7: Matrix Reshaping and Transposition; Matrix Multiplication; Exercise 8: Matrix Multiplication; Exercise 9: Tensor Multiplication; Introduction to Keras; Layer Types; Activation Functions; Model Fitting; Activity 2: Creating a Logistic Regression Model Using Keras; Summary; Chapter 3: Deep Learning with Keras; Introduction; Building Your First Neural Network; Logistic Regression to a Deep Neural Network; Activation Functions 
Summary 
Applied Deep Learning with Keras takes you from a basic knowledge of machine learning and Python to an expert understanding of applying Keras to develop efficient deep learning solutions. This book teaches you new techniques to handle neural networks, and in turn, broadens your options as a data scientist 
Notes 
CrossValidation for Model Evaluation versus Model Selection 

Description based upon print version of record 
Form 
Electronic book

Author 
Abdolahnejad, Mahla


Moocarme, Matthew

ISBN 
1838554548 

9781838554545 
