The Deep Learning Architect's Handbook

Table of Contents

Preface

Part 1 – Foundational Methods

1

Deep Learning Life Cycle

Technical requirements

Understanding the machine learning life cycle

Strategizing the construction of a deep learning system

Starting the journey

Evaluating deep learning’s worthiness

Defining success

Planning resources

Preparing data

Deep learning problem types

Acquiring data

Making sense of data through exploratory data analysis (EDA)

Data pre-processing

Developing deep learning models

Deep learning model families

The model development strategy

Delivering model insights

Managing risks

Ethical and regulatory risks

Business context mismatch

Data collection and annotation risks

Data security risk

Summary

Further reading

2

Designing Deep Learning Architectures