Deep Learning for Computer Vision with SAS: An Introduction

✍ Scribed by Robert Blanchard

• Publisher: SAS Institute
• Year: 2020
• Tongue: English
• Leaves: 205
• Category: Library

✦ Synopsis

Discover deep learning and computer vision with SAS!

Deep Learning for Computer Vision with SAS^®: An Introduction introduces the pivotal components of deep learning. Readers will gain an in-depth understanding of how to build deep feedforward and convolutional neural networks, as well as variants of denoising autoencoders. Transfer learning is covered to help readers learn about this emerging field. Containing a mix of theory and application, this book will also briefly cover methods for customizing deep learning models to solve novel business problems or answer research questions. SAS programs and data are included to reinforce key concepts and allow readers to follow along with included demonstrations.

Readers will learn how to:

• Define and understand deep learning
• Build models using deep learning techniques and SAS Viya
• Apply models to score (inference) new data
• Modify data for better analysis results
• Search the hyperparameter space of a deep learning model
• Leverage transfer learning using supervised and unsupervised methods

✦ Table of Contents

Contents
About This Book
About The Author
Chapter 1: Introduction to Deep Learning
Introduction to Neural Networks
Biological Neurons
Deep Learning
Traditional Neural Networks versus Deep Learning
Building a Deep Neural Network
Demonstration 1: Loading and Modeling Data with Traditional Neural Network Methods
Demonstration 2: Building and Training Deep Learning Neural Networks Using CASL Code
Chapter 2: Convolutional Neural Networks
Introduction to Convoluted Neural Networks
Input Layers
Convolutional Layers
Using Filters
Padding
Feature Map Dimensions
Pooling Layers
Traditional Layers
Demonstration 1: Loading and Preparing Image Data
Demonstration 2: Building and Training a Convolutional Neural Network
Chapter 3: Improving Accuracy
Introduction
Architectural Design Strategies
Image Preprocessing and Data Enrichment
Transfer Learning Introduction
Domains and Subdomains
Types of Transfer Learning
Transfer Learning Biases
Transfer Learning Strategies
Customizations with FCMP
Tuning a Deep Learning Model
Chapter 4: Object Detection
Introduction
Types of Object Detection Algorithms
Data Preparation and Prediction Overview
Normalized Locations
Multi-Loss Error Function
Error Function Scalars
Anchor Boxes
Final Convolution Layer
Demonstration: Using DLPy to Access SAS Deep Learning Technologies: Part 1
Demonstration: Using DLPy to Access SAS Deep Learning Technologies: Part 2
Chapter 5: Computer Vision Case Study
References