Cargando…
Learn Keras for deep neural networks : a fast-track approach to modern deep learning with Python /
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...
| Clasificación: | Libro Electrónico |
|---|---|
| Autor principal: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
[New York, NY] :
Apress,
[2019]
|
| Temas: | |
| Acceso en línea: | Texto completo (Requiere registro previo con correo institucional) |
Tabla de Contenidos:
- 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?
- 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