Artificial Intelligence Basics

This set of vocabulary flashcards covers the foundational concepts, history, and disciplines of Artificial Intelligence as described in the lecture notes.

Artificial Intelligence (AI)

A field that allows for the creation of machines capable of performing tasks that usually require human intelligence, with the goal of acting autonomously.

Computer Vision

A domain focused on the understanding and interpretation of images and videos by machines, used in areas like facial recognition and autonomous vehicle navigation.

Natural Language Processing (NLP)

Also known as TAL, it is a field focused on the interaction between computers and human language to understand, interpret, and respond to text or speech.

Robotics

A field centered on the design, construction, operation, and use of robots in sectors such as industry, health, and scientific research.

Machine Learning (ML)

A branch of AI focused on developing systems capable of learning and improving from experience without being explicitly programmed like traditional systems.

Deep Learning

An advanced subset of Machine Learning that uses complex neural network architectures to process data that is much larger and more complex than traditional ML.

Weak AI

AI systems currently in reality that have capabilities limited to a single specific task and do not possess consciousness or general understanding.

Strong AI

A theoretical stage of AI that would possess understanding and consciousness similar or superior to that of a human being.

Generative AI

A sub-domain of deep learning that uses artificial neural networks to create new content, such as text, images, or audio, by learning patterns from existing content.

Mathematical Model

The central core of an AI system, consisting of a structure or mathematical representation designed for problem analysis or task execution.

Learning Algorithm

Special rules that modify the parameters of a model to train it, determining how accurately the AI adapts to new information.

Supervised Learning

A type of learning that uses a known set of input data and known responses (labels) to train a model to generate predictions for new input data.

Unsupervised Learning

A type of learning used to explore data when there is no precise objective or known information/labels within the data.

Tokens

Individual units or words within human language that models analyze to reproduce relationships based on probability links.

Expert Systems

Systems developed in the 1980s capable of reproducing the logical functioning of human specialists.