Capella University AI1000 Common AI Terms

These are the terms provided by the professor in the class with their definitions.

AI (artificial intelligence)

The simulation of human intelligence processes by machines or computer systems.

Algorithm

A sequence of rules given to an AI machine to perform a task or solve a problem.

Chatbot

A software application designed to imitate human conversation through text or voice commands.

Discriminative models

used for classifying data by directly learning the boundary between different classes. EX: sorting emails and recognizing faces

Computer vision

An interdisciplinary field focusing on how computers can gain understanding from images and videos.

Multi-modal models

Systems that combine and/or convert types of data. Ex: creating text from images or answer questions about an image.

Data augmentation

The process of increasing the size and diversity of a training data set by creating modified versions of existing data points, such as rotating or scaling images.

Tabular Classification Models

Uses structured (tabled) data to categorize new data.

Embeddings

Mathematical representations of objects like text, images, and audio that enable machine learning models to understand relationships and find similarities.

Generative AI

AI technology that creates new content, such as text, images, or video, by learning patterns from large data sets.

Guardrails

Restrictions and rules placed on AI systems to ensure appropriate data handling and prevent unethical content generation.

Hallucination

An incorrect or false response from an AI system presented as factual information.

Image generation

The process of creating new images using AI models trained on large data sets of existing images.

Large language model (LLM)

An AI model trained on vast amounts of text data to understand and generate human-like language.

Locally run

This means the app and all of its data is run from the users personal computer.

Machine learning

A subset of AI that focuses on developing algorithms and models that help machines learn from data and make predictions without human assistance.

Model

A mathematical representation of a real-world process or system, used by AI to make predictions or decisions based on input data.

Natural language processing (NLP)

A type of AI that enables computers to understand spoken and written human language.

Pre-trained model

An AI model that has been trained on a large data set and can be fine-tuned for specific tasks, saving time and computational resources compared to training from scratch.

Prompt

The input given to an AI system to obtain a desired output or result.

Sentiment analysis

The process of using AI to determine the emotional tone or opinion expressed in a piece of text, such as positive, negative, or neutral.

Speech recognition

The ability of AI systems to convert spoken language into written text.

Text generation

The process of creating new text content using AI models trained on large amounts of existing text data.

Text-to-speech

The ability of AI systems to convert written text into spoken language.

Tokenization

The process of breaking down text data into smaller units called tokens, such as words or subwords, to be processed by AI models.

Training data

The information or examples given to an AI system to enable it to learn, find patterns, and create new content.

Transformer model

A type of model that has revolutionized NLP by enabling more effective handling of sequential data without processing it in order. This is the brain that runs many large language models.

Voice cloning

The ability of AI systems to generate speech that mimics a specific person's voice based on a sample of their speech data.