Learning methods, training processes, optimization and common machine-learning tasks.
The mathematical algorithm used to calculate how much each individual parameter contributed to an error.
The number of training examples the model processes before updating its internal parameters.
A machine learning task where the model predicts which predefined category or label a given input belongs to.
An unsupervised learning technique that groups data points based on mathematical similarity without requiring predefined labels.
The process of identifying raw data and assigning informative categories or tags to provide context for a machine learning model.
A specialized branch of machine learning that relies on multi-layered neural networks to process complex data.
One complete pass through the entire available training dataset by the machine learning algorithm.
An optimization algorithm used to iteratively adjust model parameters to minimize the error of its predictions.
A configuration setting chosen by the developer to govern the training process of a machine learning model.
A hyperparameter that determines the size of the mathematical adjustments a model makes during training.
A subset of artificial intelligence where systems learn patterns from data rather than following explicit programming.
The process of testing a trained AI model against a separate dataset to measure its accuracy, reliability, and safety.
The computationally intensive phase where a machine learning algorithm processes data to learn patterns and adjust its parameters.
A computing architecture inspired by the human brain, composed of interconnected nodes that process data.
A failure state where an AI model memorizes its training data so closely that it cannot accurately process new, unseen data.
A machine learning training method based on rewarding desired behaviors and penalizing undesired ones.
A machine learning technique where the model automatically generates its own labels from the raw data during training.
A machine learning approach where the model learns from a dataset containing highly structured, labeled examples.