Data Structures on English AI Terms Dictionary

Tensor

Sat, 18 Jul 2026 10:17:39 +0000

Definition

In computer science and deep learning, a tensor is a mathematical object that generalizes scalars, vectors, and matrices to higher dimensions. It is characterized by its rank (number of dimensions) and shape (size along each dimension). Tensors allow efficient computation of linear algebra operations on GPUs and TPUs, forming the backbone of neural network data flow and parameter storage in frameworks like PyTorch and TensorFlow.

Summary

A multi-dimensional array that serves as the fundamental data structure for deep learning frameworks.

Hierarchical navigable small world

Sat, 18 Jul 2026 10:01:08 +0000

Definition

The Hierarchical Navigable Small World (HNSW) algorithm constructs a multi-layered graph where each layer contains a subset of nodes from the layer below. Navigation starts at the top layer, moving closer to the target node before descending to finer layers. This structure allows for logarithmic time complexity in search operations, making it highly effective for large-scale vector databases and similarity searches in machine learning applications like recommendation systems and image retrieval.

Bloom

Sat, 18 Jul 2026 09:48:33 +0000

Definition

While historically referring to Benjamin Bloom’s educational taxonomy, in modern AI contexts, it often denotes the Bloom text embedding model developed by BigScience. This model generates high-quality vector representations for text, facilitating tasks like semantic search and clustering. Alternatively, it may refer to the ‘bloom filter’ data structure used for probabilistic set membership testing, optimizing memory usage in large-scale database and network applications.

Summary

In machine learning, ‘Bloom’ typically refers to Bloom’s Taxonomy applied to AI education or specific embedding models like the Bloom text embedding model.

Ball tree

Sat, 18 Jul 2026 09:47:37 +0000

Definition

A Ball tree partitions data points into nested hyperspheres (balls) rather than hyperrectangles. This structure allows for efficient pruning during nearest neighbor queries by calculating distances between balls rather than individual points. It is particularly advantageous in high-dimensional spaces where other structures like KD-trees may suffer from the curse of dimensionality, providing faster search times for k-NN algorithms.

Summary

A binary tree data structure used to organize points in space, optimizing nearest neighbor searches in high-dimensional datasets.

Graph

Sat, 18 Jul 2026 09:32:53 +0000

Definition

A graph is a fundamental data structure in AI comprising vertices (nodes) and edges (links) that denote relationships. Graph Neural Networks (GNNs) leverage this structure to perform learning on non-Euclidean data, such as social networks or molecular structures. Unlike grid-based data processed by CNNs, graphs allow for irregular connectivity and variable sizes. Graphs are essential for knowledge representation, reasoning, and modeling complex interactions where the relationship between items is as important as the items themselves.