Beginner · Fundamentals

Tensor

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. A multidimensional array used to represent data in many dimensions, fundamental to deep learning.

Technical Definition

A multidimensional array used to represent data in many dimensions, fundamental to deep learning.

How it works

In machine learning, especially deep learning, data is typically represented as tensors. A scalar is a 0-dimensional tensor, a vector is a 1-dimensional tensor, and a matrix is a 2-dimensional tensor. Higher-dimensional tensors are used for complex data like images (height x width x color channels) or video. Operations on tensors form the core computations in neural networks, enabling complex mathematical manipulations.