Artificial Intelligence Glossary

A

AI Ethics

AI Ethics refers to the moral principles and techniques used to ensure that AI technologies are developed and used in a responsible and equitable manner.

AI Governance

AI Governance is the legal and organizational framework put in place to manage AI development and deployment.

AI Tools

AI Tools refer to a variety of software and technologies used for creating, implementing, and managing artificial intelligence applications.

Artificial Intelligence (AI)

AI is the theory and development of computer systems able to perform tasks that normally require human intelligence.

Augmented Intelligence

Augmented Intelligence refers to the enhancement of human decision-making through AI systems.

AutoML (Automated Machine Learning)

AutoML refers to automated methods for applying machine learning to real-world problems.

B

Backpropagation

Backpropagation is a method used to train deep neural networks by calculating and propagating the error gradient.

Bayesian Network

A Bayesian network is a probabilistic graphical model that uses Bayesian inference for probability computations.

BERT (Bidirectional Encoder Representations from Transformers)

BERT is a transformer-based machine learning technique for NLP pre-training.

C

Capsule Networks

Capsule Networks are a type of artificial neural network designed for efficiency in visual data processing.

Chatbots

Chatbots are AI programs designed to simulate human conversation.

Computer Vision

Computer vision deals with how computers can gain high-level understanding from digital images or videos.

Convolutional Neural Network (CNN)

CNNs are deep neural networks often used for image recognition tasks.

D

Data Fabric

Data Fabric is an architectural framework for seamless integration and access to data across different platforms.

Data Mining

Data mining is the process of discovering patterns and knowledge from large amounts of data.

Decision Tree

A decision tree is a model of decisions and their possible consequences, used in predictive modeling.

Deep Learning

Deep learning is a subset of ML based on artificial neural networks with representation learning.

Differential Privacy

Differential Privacy ensures individual privacy in datasets used for AI and data analytics.

E

Edge AI

Edge AI refers to AI algorithms processed locally on a hardware device.

Ensemble Learning

Ensemble learning uses multiple learning algorithms for better predictive performance.

Evolutionary Algorithms

Evolutionary algorithms use biological evolution-inspired mechanisms to solve optimization problems.

F

Feature Engineering

Feature engineering is the process of selecting and transforming variables in machine learning.

Federated Learning

Federated Learning is where the model is trained across multiple decentralized devices.

Fuzzy Logic

Fuzzy Logic is a computational approach known for its basis in human reasoning.

G

Genetic Algorithm

A genetic algorithm is a search heuristic inspired by Darwin's theory of natural evolution.

Gradient Descent

Gradient Descent is an optimization algorithm used to minimize a function iteratively.

H

Heuristic

A heuristic is a practical approach to problem-solving prioritizing speed over precision.

Hyperparameters

Hyperparameters define the structure and behavior of an AI model.

I

Image Recognition

Image Recognition is the AI's ability to identify objects, places, people, writing, and actions in images.

Inductive Learning

Inductive Learning is learning by examples, where a system tries to induce a general rule from observed instances.

J

Jupyter Notebook

Jupyter Notebook is an open-source web application for creating and sharing documents with live code, equations, visualizations, and narrative text.

JSON (JavaScript Object Notation)

JSON is a lightweight data-interchange format easy for humans to read and machines to parse and generate.

K

Keras

Keras is a user-friendly neural network library written in Python for various machine learning frameworks.

K-means

K-means is an unsupervised machine learning algorithm used for item classification based on feature similarity.

L

Linear Regression

Linear Regression is a supervised learning algorithm for predicting values based on other variables.

Logistic Regression

Logistic Regression is a machine learning algorithm for classification problems.

M

Machine Learning (ML)

Machine Learning is a type of AI that provides computers with the ability to learn without explicit programming.

Metalearning

Metalearning, or learning to learn, involves AI systems learning new tasks with minimal data.

Monte Carlo Method

Monte Carlo methods are computational algorithms that rely on repeated random sampling for numerical results.

N

Natural Language Processing (NLP)

NLP focuses on how computers can understand and manipulate human language.

Neural Network

Neural Networks are algorithms modeled after the human brain, designed to recognize patterns.

Neuro-Symbolic AI

Neuro-Symbolic AI combines neural networks with symbolic AI for learning, reasoning, and understanding.

O

Ontology

In computer science, an ontology encompasses a representation, formal naming, and definition of the categories, properties, and relations of the concepts, data, and entities.

Overfitting

Overfitting is when a statistical model describes random error or noise instead of the underlying relationship.

P

Perceptron

The perceptron is an algorithm for supervised learning of binary classifiers.

Python

Python is a high-level programming language often used in artificial intelligence projects.

Q

Q-Learning

Q-Learning is a reinforcement learning algorithm to learn what action to take under various circumstances.

Quantum Computing

Quantum computing uses quantum bits for simultaneous calculations, impacting AI and machine learning.

R

Random Forest

Random Forest is a machine learning algorithm using multiple decision trees for better predictive accuracy.

Reinforcement Learning

Reinforcement Learning is where an agent learns to behave in an environment by performing actions and seeing results.

Reinforcement Learning 2.0

An advanced form of Reinforcement Learning, incorporating deeper contextual understanding.

S

Supervised Learning

Supervised Learning is where the model learns from labeled data.

SVM (Support Vector Machine)

SVM is a supervised machine learning model for two-group classification problems.

Synthetic Data Generation

This refers to the creation of artificial data by AI algorithms for training machine learning models.

T

TensorFlow

TensorFlow is a software library for machine learning, particularly in training deep neural networks.

Transfer Learning

Transfer Learning is where a model developed for one task is reused for another.

U

Underfitting

Underfitting occurs when a model cannot capture the underlying trend of the data.

Unsupervised Learning

Unsupervised Learning draws inferences from datasets without labeled responses.

V

Validation Set

A validation set is a set of examples used to tune the parameters of a classifier.

Variable

In machine learning, a variable is any characteristic, number, or quantity that can be measured or counted.

W

Weights

In machine learning, weights are the coefficients assigned to different features in the data.

Word Embedding

Word Embedding allows words with similar meanings to have similar vector representations.

X

XGBoost

XGBoost stands for eXtreme Gradient Boosting, a software library for a gradient boosting framework.

XOR Problem

The XOR problem is a classification problem where the classes are linearly inseparable.

Y

YOLO (You Only Look Once)

YOLO is a real-time object detection system that identifies objects in a single glance.

Yottabyte

A Yottabyte is a measure of data storage capacity, equivalent to one septillion bytes.

Z

Z-Score

A Z-score represents how many standard deviations an element is from the mean in machine learning.

Zero-Shot Learning

Zero-Shot Learning refers to a machine's ability to recognize objects and concepts it has not been trained on.