How deeply does Deep Learning with R, Third Edition cover problem domain?

Explains domain reasoning as a prerequisite for modeling but stops short of replacing it with Keras or TensorFlow tools.

Problem domain

As explained in Deep Learning with R, Third Edition

A problem domain is the real-world subject area and context in which a machine learning task is defined and applied.

A problem domain is the real-world subject area and business context that determine what a machine learning system should predict, which data represents the task, and how success should be measured. section 6.0 section 20.1.5

Finding unknown archaeological sites

A task involving as-yet-unknown archaeological sites cannot begin with model fitting alone. Understanding the domain helps establish the prediction target, identify suitable data, and choose a meaningful measure of success. section 6.0 section 20.1.5

Use the problem domain to guide the machine learning workflow:

Define what the system should predict and what data is available. section 20.1.5
Determine whether additional data collection or manual labeling is necessary. section 20.1.5
Choose reliable success measures, including domain-specific metrics when accuracy is insufficient. section 20.1.5

How Deep Learning with R, Third Edition covers it

Cover of Deep Learning with R, Third Edition

liveBook manning.com

Read Deep Learning with R, Third Edition on liveBook Get the book at manning.com

Related concepts

machine learning workflowpart of · A machine learning workflow is an organized sequence of activities for formulating, developing, evaluating, deploying, operating, and maintaining a machine learning system.
constraintconfigures · A constraint is a condition or rule that restricts the permissible states, values, actions, or solutions in a system or problem.
inputproduces · An input is a value, information, or signal supplied to a system, computation, or interface for processing or to influence its behavior.
machine learning problemhas part · A machine learning problem is a defined predictive or analytical task in which a model learns patterns from data to produce useful outputs.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with R, Third Edition. The section links point to the parts of the book it draws on.