# What is Tensor? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Mathematical Foundations  
> **Canonical Citation:** [https://spidits.com/ai-glossary/tensor](https://spidits.com/ai-glossary/tensor)

## Definition
A Tensor is a multi-dimensional mathematical array of numbers that serves as the fundamental data structure for representing inputs, weights, and activations in deep learning frameworks like TensorFlow and PyTorch.

## Architectural Mechanics & Deep Dive
A tensor is a multi-dimensional mathematical array of numbers, generalizing scalars (0D), vectors (1D), and matrices (2D) to higher dimensions. In deep learning frameworks (like PyTorch and TensorFlow), tensors are the primary data structures used to store and manipulate inputs, activations, and neural network weights.

## Industry Applications & Real-World Use Cases
Representing batches of color images (4D tensor: batch size, height, width, channels) and tracking gradients during backpropagation.

## Frequently Asked Questions

### How does a tensor differ from a matrix or vector?
A vector is a 1D tensor, a matrix is a 2D tensor, and tensors can extend to three or more dimensions (e.g., 3D, 4D, 5D tensors).

### Why are GPUs highly efficient at processing tensors?
GPUs contain thousands of small arithmetic cores designed to perform matrix and tensor mathematical operations (like dot products and additions) in parallel.

## Related Terminology
- [pytorch](https://spidits.com/ai-glossary/pytorch)
- [gpu](https://spidits.com/ai-glossary/gpu)
- [embedding-dimension](https://spidits.com/ai-glossary/embedding-dimension)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*