Bandit Algorithm

Semi-Supervised Learning

A learning approach that combines a small amount of labelled data with a large amount of unlabelled data during training.

Self-Supervised Learning

A learning paradigm where models generate their own supervisory signals from unlabelled data through pretext tasks.

Transfer Learning

A technique where knowledge gained from training on one task is applied to a different but related task.

Meta-Learning

Learning to learn — algorithms that improve their learning process by leveraging experience from multiple learning episodes.

Curriculum Learning

A training strategy that presents examples to a model in a meaningful order, typically from easy to hard.

Bagging

Bootstrap Aggregating — an ensemble method that trains multiple models on random subsets of data and averages their predictions.

Errors or inconsistencies in the annotations of training data that can degrade model performance and lead to unreliable predictions if not properly addressed.

The infrastructure and processes for deploying trained machine learning models to production environments for real-time predictions.

An optimisation algorithm that iteratively adjusts parameters in the direction of steepest descent of the loss function.

The application of deep neural networks to structured tabular datasets, competing with traditional methods like gradient boosting through specialised architectures and regularisation.

A technique that decomposes a matrix into constituent matrices, widely used in recommendation systems and dimensionality reduction.

A regularised regression technique that adds an L1 penalty, enabling feature selection by driving some coefficients to zero.

A mathematical framework for modelling sequential decision-making where outcomes are partly random and partly controlled.

Techniques that reduce the number of input variables in a dataset while preserving essential information and structure.