liveBook · Manning

Vector description

As explained in Deep Learning with R, Third Edition

Vector data represents each data instance as a one-dimensional vector of numerical attributes.

A vector description encodes each data instance as a one-dimensional vector of numerical attributes, or features. A dataset then becomes a rank-2 tensor: samples form the first axis, and features form the second. section 2.2.8

Two concrete datasets

Represent each person by age, gender, and income; 100,000 people form a tensor with shape (100000, 3). Represent each document by word counts from a 20,000-word dictionary; 500 documents form shape (500, 20000). section 2.2.8

How Deep Learning with R, Third Edition covers it

How deep it goes
Defines rank-2 structure, sample and feature axes, and concrete shapes without developing implementation details.
Examples
Uses actuarial records with age, gender, and income plus document word-count vectors.
What you can do after
Operate data as rank-2 tensors by distinguishing sample rows from numerical feature columns.
How it connects
Connects vector data with tensors, features, samples, timeseries data, sequence data, images, and video.
Cover of Deep Learning with R, Third Edition
liveBookmanning.com
Read Deep Learning with R, Third Edition on liveBook Get the book at manning.com

Related concepts

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.