Artificial Intelligence - Module 8.b

This set of flashcards covers key vocabulary and concepts from the lecture on Artificial Intelligence, including its various branches and applications.

Artificial Intelligence (AI)

A field of computer science focused on creating systems that can perform tasks typically requiring human intelligence.

Machine Learning (ML)

A subset of AI that involves the use of algorithms and statistical models that enable computers to improve their performance on a task through experience.

Deep Learning (DL)

A specialized form of machine learning that uses neural networks with many layers to analyze various factors of data.

Classical AI

Also known as GOFAI (Good Old Fashioned AI), it involves symbolic reasoning and deterministic outcomes based on predefined rules.

Algorithm

A step-by-step procedure or formula for solving a problem.

Heuristic

Experience-based techniques for problem-solving, learning, and discovery that provide a solution that is not guaranteed to be optimal but is sufficient for reaching an immediate goal.

Expert System

A computer system that emulates the decision-making ability of a human expert, using a knowledge base and rules.

Reinforcement Learning

A type of machine learning where an agent learns to behave in an environment by performing actions and receiving rewards or penalties.

Supervised Learning

A branch of machine learning where the model is trained using labeled data.

Unsupervised Learning

A type of machine learning that involves training a model without labeled responses, discovering patterns or groupings in the data.

Neural Network

A computational model inspired by the way biological neural networks in the human brain work, consisting of interconnected groups of nodes.

Feature Engineering

The process of selecting, modifying, or creating features from raw data to improve model performance.

Training Data

The dataset used to train a model; it includes both input data and the corresponding correct output.

Testing Data

The dataset used to evaluate the performance of a trained model to ensure it works properly with new data.

Bias

An error introduced by approximating a real-world problem, which may lead to a model's inability to generalize.

Dimensionality Reduction

The process of reducing the number of random variables under consideration, obtaining a set of principal variables.

Applications of Machine Learning

Fields where machine learning is utilized, including social media features, stock market trading, medical diagnosis, and automatic translation.

Overfitting

A modeling error that occurs when a machine learning model captures noise in the data instead of the intended outputs.

Data Preparation

The process of cleaning, transforming, and organizing data into a suitable format for analysis or model training.