Supervised Learning

These terms represent key concepts and methodologies that underpin supervised learning, one of the primary categories of machine learning, where the focus is on learning a function that maps input data to known output labels.

Accuracy - A measure of how correct a supervised learning model's predictions are, commonly used as an evaluation metric.

Action Recognition - The task of identifying a sequence of actions being performed in a video.

Agent - In the context of supervised learning, it could refer to a system or model that is trained to perform specific tasks, making decisions based on data and the associated outcomes.

Anomaly Detection - The identification of unusual data points, which differ significantly from the majority of the data.

Artificial Neural Network (ANN) - A computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs.

Autoencoder - In supervised contexts, it can be used for tasks like feature learning and dimensionality reduction, where the output targets are the inputs themselves.

Automated Machine Learning (AutoML) - Automating the process of applying machine learning to real-world problems with minimal human intervention.

Classification - A type of supervised learning task where the goal is to predict discrete labels, categorizing input data into two or more classes.

Code Generation - The process of automatically writing code based on the requirements or data provided, which can be considered a form of supervised learning if the model is trained on code datasets.

Convolutional Neural Network (CNN) - Used in supervised learning for tasks such as image and video recognition, classification, and segmentation.

Cross-Validation - A technique used in supervised learning to assess the generalizability of a model by partitioning the data into subsets, training the model on one subset, and validating it on another.

Data Cleaning - The practice of preparing data for analysis by removing or modifying data that is incorrect, incomplete, irrelevant, duplicated, or improperly formatted.

Deep Learning (DL) - A subset of machine learning in artificial intelligence with networks capable of learning unsupervised from data that is unstructured or unlabeled.

Dimensionality Reduction - The transformation of high-dimensional data into a meaningful representation of reduced dimensionality.

Facial Recognition - A technology capable of identifying or verifying a person from a digital image or a video frame.

Feature Engineering - The process of using domain knowledge to extract features from raw data that make machine learning algorithms work.

Image Recognition - The ability of AI systems to identify objects, places, and actions in images.

Label - In supervised learning, a label is the known output or result for a given input data point, used for training the model.

Labeled Data - Data that includes both input features and the corresponding target outputs (labels), essential for training supervised learning models.

Loss Function - A function that measures the discrepancy between the actual and predicted outputs in supervised learning, guiding the optimization process during model training.

Machine Learning (ML) - The scientific study of algorithms and statistical models that computer systems use to effectively perform a specific task without using explicit instructions.

Natural Language Generation (NLG) - The use of AI to generate text from a computer database.

Regression - A type of supervised learning task that involves predicting continuous outcomes based on input variables.

Reinforcement Learning (RL) - Although typically an unsupervised learning paradigm, it can be adapted for supervised tasks, where the model is trained to make a sequence of decisions.

Supervised Learning - A machine learning paradigm where models learn to predict outcomes based on input data that is paired with known output data (labels), allowing the model to be explicitly taught the relationships within the data.

Target Variable - The variable that a supervised learning model is trained to predict, synonymous with "label" in the context of a dataset.

Train vs. Test - Refers to the practice in supervised learning of dividing a dataset into a training set, used to train the model, and a test set, used to evaluate the model's performance on unseen data.

Video Data - The use of video data in supervised learning tasks such as action recognition, object detection, and more.