A Glossary of Artificial Intelligence Terms
If you are interested in the artificial intelligence (AI) field there are a large number of fundamental terms you should know. This article covers 17 of the most common AI terms.
Algorithm
A process or set of rules for performing a task, oftentimes as a formula or a well-defined set of instructions for the computer. AI researchers use algorithms to tell a machine how to go about finding answers to a question or solutions to a problem.
Artificial Intelligence (AI)
A field of computer science dedicated to the study of computer software making intelligent decisions, reasoning, and problem solving with subsets that include machine learning and deep learning.
Autonomous
Autonomy is the ability to act independently of a ruling body. In AI, a machine or vehicle is referred to as autonomous if it doesn’t require input from a human operator to function properly (i.e. self-driving cars).
Bias
There are two types of bias in AI. The first is data bias, where training is done with biased data that is prejudiced or predetermined to create a specific result. The second is societal, where researchers expect a certain outcome prior to training the data and getting their results.
Computer Vision
A field of artificial intelligence that seeks to process images and videos similar to how humans process visual imagery in order to understand and automate tasks like people do.
Convolutional Neural Networks (CNN)
A class of deep learning neural network designed primarily for processing images or structured data arrays.
Dataset
A collection of data. AI researchers use datasets to train neural networks to a desired outcome or discover new outcomes.
Deep Learning
A subset of machine learning that uses specialized algorithms to model and understand complex structures and relationships among data and datasets.
Generative Adversarial Network (GAN)
An unsupervised machine learning architecture that trains two neural networks by forcing them to “outwit” each other. These can be used for creating deepfakes or artificial images for testing purposes, such as with medical MRI images of brain tumors.
Machine Learning
A field of AI focused on getting machines to act without being programmed to do so. Machines “learn” from historical data and patterns they recognize and adjust their behavior accordingly.
Model
A program that has been trained on a set of data (called the training set) to recognize certain types of patterns.
Natural Language Processing (NLP)
The ability of computers to understand, or process natural human languages and derive meaning from them. NLP typically involves machine interpretation of text or speech recognition and is widely used in chatbots, email filters, predictive text, and voice activated assistants like Siri and Alexa.
Neural Network
A computer system modeled on the human brain and nervous system and designed to process information the way humans do.
Recurrent Neural Network (RNN)
A type of neural network where connections between nodes form a directed graph along a temporal sequence. This type of neural network is commonly used in speech recognition and natural language processing.
Supervised Learning
A machine learning method that allows the model to work on its own to discover patterns and information that was previously undetected. It mainly deals with the data that is not labeled.
Unsupervised Learning
A machine learning method that learns from labeled training data to help you predict outcomes for unforeseen data.
Weights
The connection strength between units, or nodes, in a neural network. These weights can be adjusted in a process called learning.
Take a look at the SabrePC blog to view additional articles related to AI, deep learning, machine learning or a variety of other topics, or contact us for any questions.
Interested in a deep learning solution for AI research?
Get a workstation with up to 2x NVIDIA RTX 3070/3080/3090 starting at only $3,700