Machine Learning
Machine Learning (ML) is a subfield of AI in which systems learn statistical patterns from data rather than being explicitly programmed with rules.
What is Machine Learning?
Machine Learning algorithms include linear and logistic regression, decision trees, random forests, gradient-boosted trees, support vector machines, and neural networks. ML projects typically involve a labelled training set, a held-out validation set, and an evaluation harness measuring accuracy, precision, recall, F1, or business-specific metrics. ML systems can be supervised (trained on labelled examples), unsupervised (find structure in unlabelled data), or reinforcement-based (learn from rewards). Most enterprise ML in production is supervised classification or regression on tabular or text data.
How does Machine Learning apply to enterprise AI?
Enterprises use ML for credit scoring, claims triage, churn prediction, document classification, and anomaly detection. Under the EU AI Act, many such systems qualify as high-risk and require conformity assessment, data governance, and post-market monitoring.
Related terms
- Deep Learning - Deep Learning is a branch of machine learning that uses multi-layer neural networks to learn hierarchical representations from raw data.
- Neural Network - A neural network is a computational model loosely inspired by biological neurons, in which weighted connections between simple units learn to map inputs to outputs.
- Model Drift - Model drift is the gradual or sudden degradation of a model's performance in production caused by changes in input data, target distribution, or operating context.
- Evaluation Harness - An evaluation harness is the test framework used to measure an AI system against a fixed set of inputs, expected outputs, and metrics, run on every change.
External references
Need help applying Machine Learning to your enterprise? Submit a short brief and we reply within one business day.