AI Glossary

Advanced AI Glossary

Comprehensive reference for artificial intelligence terms, concepts, and technologies

A

Artificial Intelligence (AI)

Beginner

1. The simulation of human intelligence processes by machines, especially computer systems. These processes include learning, reasoning, and self-correction.

2. A broad field of computer science focused on creating systems capable of performing tasks that typically require human intelligence.

Fundamental Concepts

Attention Mechanism

Advanced

1. A component in neural networks that dynamically weighs the importance of different parts of the input data.

2. A technique that mimics cognitive attention by focusing on relevant parts of the input while processing data.

Components

C

Computer Vision

Intermediate

1. A field of AI that trains computers to interpret and understand the visual world.

2. The science and technology of machines that see, where see in this case means that the machine is able to extract information from an image.

Applications

D

Deep Learning

Advanced

1. A subset of machine learning that uses multi-layered neural networks to analyze various factors of data.

2. Machine learning techniques based on learning data representations, as opposed to task-specific algorithms.

Core Technologies

E

Ethical AI

Intermediate

1. The branch of ethics that examines how to maximize the benefits of AI while minimizing its risks and negative consequences.

2. The study and implementation of AI systems that align with moral principles and societal values.

Governance

Explainable AI (XAI)

Intermediate

1. Methods and techniques in the application of AI technology such that the results of the solution can be understood by human experts.

2. AI systems that provide explanations for their decisions and predictions in a way that humans can understand.

Approaches

G

Generative Adversarial Network (GAN)

Advanced

1. A class of machine learning frameworks where two neural networks contest with each other in a game (generator vs. discriminator).

2. An unsupervised learning system where two networks compete: one generates candidates while the other evaluates them.

Models

L

Large Language Model (LLM)

Intermediate

1. A type of AI model that processes and generates human-like text based on massive datasets, powering applications like chatbots and content generation tools.

2. Neural networks with billions of parameters trained on vast amounts of text data to understand and generate human language.

Models

M

Machine Learning (ML)

Intermediate

1. A subset of AI that enables systems to automatically learn and improve from experience without being explicitly programmed.

2. The study of computer algorithms that improve automatically through experience and by the use of data.

Core Technologies

N

Neural Network

Intermediate

1. A series of algorithms that attempts to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates.

2. A computing system inspired by biological neural networks that constitute animal brains, consisting of interconnected nodes that process information.

Core Technologies

Natural Language Processing (NLP)

Intermediate

1. A branch of AI that helps computers understand, interpret, and manipulate human language.

2. The application of computational techniques to the analysis and synthesis of natural language and speech.

Applications

P

Prompt Engineering

Intermediate

1. The practice of designing and refining inputs (prompts) to get the desired outputs from AI models, particularly in generative AI systems.

2. The art and science of crafting inputs that effectively communicate with AI systems to produce optimal results.

Techniques

Q

Quantum Machine Learning

Advanced

1. The integration of quantum algorithms within machine learning programs.

2. An emerging field that explores how quantum computing can enhance machine learning tasks.

Emerging Technologies

R

Reinforcement Learning

Advanced

1. An area of machine learning concerned with how software agents ought to take actions in an environment to maximize some notion of cumulative reward.

2. Learning through interaction with an environment where the agent receives rewards or penalties for actions.

Learning Methods

T

Transformer Architecture

Advanced

1. A deep learning model architecture that has revolutionized natural language processing, using self-attention mechanisms to process sequential data.

2. An architecture that handles sequential data without using recurrence, relying entirely on attention mechanisms to draw global dependencies between input and output.

Architectures