AI Glossary
Welcome to our comprehensive AI Glossary, a curated collection of key terms and concepts essential for understanding the ever-evolving world of artificial intelligence.
Knowledge Graph
A network that links entities and their relationships
Latent Variable
A variable that's not directly observed but inferred from other observed variables
Learning Rate
A hyperparameter that determines the step size at which a machine learning model learns during training.
Loss Function
A mathematical function that quantifies how well a machine learning model is performing; the goal is to minimize this function during training.
Machine Learning
A type of artificial intelligence that enables a system to learn from data rather than through explicit programming.
Model
A mathematical representation of a real-world process based on the data provided to the machine learning algorithm.
Natural Language Processing (NLP)
A subfield of AI focused on enabling machines to understand and respond to human language.
Neural Network
A machine learning model inspired by the human brain
Normalisation
The process of scaling data to a standard range
Object Recognition
The ability of AI systems to identify and categorize objects within images or videos.
Overfitting
A situation where a machine learning model learns the noise in the training data
Parameter
A variable in a machine learning model that's learned from the training data.
Recurrent Neural Network (RNN)
A type of neural network well-suited for time-series data or sequential data.
Regression
A type of machine learning task where the goal is to predict a continuous value.
Reinforcement Learning
A type of machine learning where an agent learns how to behave in an environment by performing actions and observing the rewards of those actions.
Supervised Learning
A type of machine learning where the model is trained on a labeled dataset—that is
Transfer Learning
The practice of reusing a pre-trained model on a new
Unsupervised Learning
A type of machine learning where the model is trained on an unlabeled dataset to discover patterns and relationships in the data.
Validation Set
A subset of the dataset used to evaluate the performance of a machine learning model during training.
Variable Importance
An assessment of the impact of each feature or variable on the performance of a machine learning model.
Vector
A sequence of numbers representing a point in space
Weight
Values in a neural network that are learned from the training data and used to make predictions or decisions.
Word Embedding
A type of representation where words or phrases are converted into vectors of real numbers
Zero-Shot Learning
A type of machine learning where the model is able to perform tasks for which it has seen no examples at all during training.