Overview
Combining deep neural networks with reinforcement learning to enable agents to learn complex decision-making from raw sensory input.
Cross-References(1)
More in Machine Learning
Lasso Regression
Feature Engineering & SelectionA regularised regression technique that adds an L1 penalty, enabling feature selection by driving some coefficients to zero.
Multi-Task Learning
MLOps & ProductionA machine learning approach where a model is simultaneously trained on multiple related tasks to improve generalisation.
Cross-Validation
Training TechniquesA resampling technique that partitions data into subsets, training on some and validating on others to assess model generalisation.
Dimensionality Reduction
Unsupervised LearningTechniques that reduce the number of input variables in a dataset while preserving essential information and structure.
Supervised Learning
MLOps & ProductionA machine learning paradigm where models are trained on labelled data, learning to map inputs to known outputs.
Regularisation
Training TechniquesTechniques that add constraints or penalties to a model to prevent overfitting and improve generalisation to new data.
Support Vector Machine
Supervised LearningA supervised learning algorithm that finds the optimal hyperplane to separate different classes in high-dimensional space.
Unsupervised Learning
MLOps & ProductionA machine learning approach where models discover patterns and structures in data without labelled examples.