Explore UAB
AI Office of the President

General AI Concepts

Artificial Intelligence (AI)
A branch of computer science focused on creating systems capable of performing tasks that would typically require human intelligence.
Algorithm
A set of rules or procedures for solving a problem, often implemented in computer code.
Data Set
A collection of data used to train or test AI models.
Inference
The process of using a trained AI model to make predictions or decisions based on new data.

Machine Learning Concepts

Machine Learning (ML)
A subset of AI that allows computers to learn from data and make decisions without explicit programming.
Supervised Learning
A type of machine learning where an algorithm is trained on labeled data.
Unsupervised Learning
A type of machine learning where an algorithm learns patterns from unlabeled data.
Reinforcement Learning
A type of machine learning where an agent learns to make decisions by interacting with an environment to achieve a goal.
Overfitting
When an AI model learns the training data too well, including its noise and outliers, and performs poorly on new, unseen data.
Underfitting
When an AI model is too simple to capture the underlying patterns in the data, leading to poor performance.
Feature Extraction
The process of selecting or transforming variables (features) from the data to improve an AI model's performance.

Deep Learning Concepts

Deep Learning
A specialized form of machine learning inspired by the architecture and function of the brain, using neural networks with many layers.
Neural Network
A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons).
Convolutional Neural Network (CNN)
A type of neural network particularly effective for tasks like image recognition.
Recurrent Neural Network (RNN)
A type of neural network designed to handle sequential data like time series or natural language.
Backpropagation
The primary algorithm for performing gradient descent on neural networks, used to minimize the error in the model's predictions.
Activation Function
A mathematical function applied to a node in a neural network, determining the node's output.

Generative AI Concepts

Generative AI
A branch of AI focused on creating new data that resembles a given dataset.
Generative Adversarial Network (GAN)
A type of neural network used for generative tasks, consisting of a Generator and a Discriminator that are trained together.
Autoencoder
A type of neural network used for unsupervised learning, often for dimensionality reduction or feature learning.
Transformer Architecture
A type of neural network architecture particularly effective for tasks involving sequences, like natural language processing.

Ethical and Social Concepts

Algorithmic Bias
Systematic errors in the functioning of an AI model that produce unfair or discriminatory outcomes.
Explainability
The ability to understand and interpret the decisions made by an AI model.
Data Privacy
The ethical handling, protection, and usage of data, particularly sensitive or personal information.