Learn Keras for deep neural networks : a fast-track approach to modern deep learning with Python / Jojo Moolayil
- Moolayil, Jojo
- [New York, N.Y.] : Apress, 
- Physical Description:
- 1 online resource
- Intro; Table of Contents; About the Author; About the Technical Reviewer; Acknowledgments; Introduction; Chapter 1: An Introduction to Deep Learning and Keras; Introduction to DL; Demystifying the Buzzwords; What Are Some Classic Problems Solved by DL in Today's Market?; Decomposing a DL Model; Exploring the Popular DL Frameworks; Low-Level DL Frameworks; Theano; Torch; PyTorch; MxNet; TensorFlow; High-Level DL Frameworks; A Sneak Peek into the Keras Framework; Getting the Data Ready; Defining the Model Structure; Training the Model and Making Predictions; Summary; Chapter 2: Keras in Action, Setting Up the EnvironmentSelecting the Python Version; Installing Python for Windows, Linux, or macOS; Installing Keras and TensorFlow Back End; Getting Started with DL in Keras; Input Data; Neuron; Activation Function; Sigmoid Activation Function; ReLU Activation Function; Model; Layers; Core Layers; Dense Layer; Dropout Layer; Other Important Layers; The Loss Function; Optimizers; Stochastic Gradient Descent (SGD); Adam; Other Important Optimizers; Metrics; Model Configuration; Model Training; Model Evaluation; Putting All the Building Blocks Together; Summary, Chapter 3: Deep Neural Networks for Supervised Learning: RegressionGetting Started; Problem Statement; Why Is Representing a Problem Statement with a Design Principle Important?; Designing an SCQ; Designing the Solution; Exploring the Data; Looking at the Data Dictionary; Finding Data Types; Working with Time; Predicting Sales; Exploring Numeric Columns; Understanding the Categorical Features; Data Engineering; Defining Model Baseline Performance; Designing the DNN; Testing the Model Performance; Improving the Model; Increasing the Number of Neurons; Plotting the Loss Metric Across Epochs, Testing the Model ManuallySummary; Chapter 4: Deep Neural Networks for Supervised Learning: Classification; Getting Started; Problem Statement; Designing the SCQ; Designing the Solution; How Can We Identify a Potential Customer?; Exploring the Data; Data Engineering; Defining Model Baseline Accuracy; Designing the DNN for Classification; Revisiting the Data; Standardize, Normalize, or Scale the Data; Transforming the Input Data; DNNs for Classification with Improved Data; Summary; Chapter 5: Tuning and Deploying Deep Neural Networks; The Problem of Overfitting; So, What Is Regularization?, and L1 RegularizationL2 Regularization; Dropout Regularization; Hyperparameter Tuning; Hyperparameters in DL; Number of Neurons in a Layer; Number of Layers; Number of Epochs; Weight Initialization; Batch Size; Learning Rate; Activation Function; Optimization; Approaches for Hyperparameter Tuning; Manual Search; Grid Search; Random Search; Further Reading; Model Deployment; Tailoring the Test Data; Saving Models to Memory; Retraining the Models with New Data; Online Models; Delivering Your Model As an API; Putting All the Pieces of the Puzzle Together; Summary; Chapter 6: The Path Ahead
- Learn, understand, and implement deep neural networks in a math- and programming-friendly approach using Keras and Python. The book focuses on an end-to-end approach to developing supervised learning algorithms in regression and classification with practical business-centric use-cases implemented in Keras. The overall book comprises three sections with two chapters in each section. The first section prepares you with all the necessary basics to get started in deep learning. Chapter 1 introduces you to the world of deep learning and its difference from machine learning, the choices of frameworks for deep learning, and the Keras ecosystem. You will cover a real-life business problem that can be solved by supervised learning algorithms with deep neural networks. You'll tackle one use case for regression and another for classification leveraging popular Kaggle datasets. Later, you will see an interesting and challenging part of deep learning: hyperparameter tuning; helping you further improve your models when building robust deep learning applications. Finally, you'll further hone your skills in deep learning and cover areas of active development and research in deep learning. At the end of Learn Keras for Deep Neural Networks, you will have a thorough understanding of deep learning principles and have practical hands-on experience in developing enterprise-grade deep learning solutions in Keras. You will: Master fast-paced practical deep learning concepts with math- and programming-friendly abstractions. Design, develop, train, validate, and deploy deep neural networks using the Keras framework Use best practices for debugging and validating deep learning models Deploy and integrate deep learning as a service into a larger software service or product Extend deep learning principles into other popular frameworks.
- 1484242408 (electronic book)
9781484242407 (electronic bk.)
- Digital File Characteristics:
- text file
- Place of publication from publisher website.
What's Next for DL Expertise?
- Bibliography Note:
- Includes bibliographical references.
View MARC record | catkey: 37448394