Unit One – What Is Artificial Intelligence?

These flashcards cover fundamental concepts related to Artificial Intelligence, its definitions, key figures like Alan Turing, types of AI, and critical debates surrounding AI understanding.

Machine Learning (ML)

A subset of AI focused on developing algorithms that allow computers to learn from and make predictions based on data without being explicitly programmed for every task.

Supervised Learning

A learning approach where an AI is trained on a labeled dataset, meaning the input data is already tagged with the correct output.

Unsupervised Learning

A learning approach where an AI identifies patterns or structures in data that has no pre-existing labels or categories.

Neural Networks

Computational models inspired by the human brain's biological structure, consisting of interconnected nodes or "neurons" organized in layers.

Deep Learning

A sophisticated form of machine learning that utilizes neural networks with many layers (n > 1) to extract high-level features from data.

The Chinese Room Argument

A thought experiment by John Searle intended to show that a machine can follow rules to manipulate symbols without actually "understanding" their meaning.

Natural Language Processing (NLP)

A branch of AI that gives computers the ability to understand, interpret, and generate human language, both written and spoken.

Heuristics

Practical strategies or "rules of thumb" used by AI systems to find solutions more quickly when exhaustive searches are impossible.

Expert Systems

Early AI programs designed to solve complex problems in specific domains by mimicking the decision-making ability of a human expert through an extensive set of "if-then" rules.

Algorithm

A finite set of unambiguous instructions or a procedure for solving a mathematical problem or performing a specific task.

Reinforcement Learning

A machine learning paradigm where an agent learns to make decisions by performing actions in an environment to achieve the maximum cumulative reward.

Overfitting

A modeling error that occurs when a machine learning model is too closely aligned to its training data, resulting in poor performance on new, unseen data.

Turing Test

A test of a machine's ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human, proposed by Alan Turing in 1950.

Computer Vision

A field of AI that enables computers and systems to derive meaningful information from digital images, videos, and other visual inputs.

Generative AI

A type of AI system capable of generating text, images, or other media in response to prompts, typically by learning the patterns of existing data.

Transformer

A deep learning model architecture that uses self-attention mechanisms, serving as the foundational technology for modern large language models.

Backpropagation

Short for "backward propagation of errors," it is the primary algorithm used to train neural networks by updating weights based on the gradient of the loss function.

Artificial General Intelligence (AGI)

A theoretical form of AI that possesses the ability to understand, learn, and apply its intelligence to any intellectual task that a human being can perform.

Training Data

The initial dataset used to teach a machine learning model how to identify patterns, make decisions, or perform specific tasks.

Large Language Model (LLM)

A sophisticated AI model trained on massive amounts of text data to understand, summarize, and generate human-like language.