Fine-tuning (Machine Learning).

Fine-tuning is the process of taking a pre-trained machine learning model and training it further on a smaller, specialized dataset. This adapts a general-purpose model to perform exceptionally well on a specific task or domain.

Fine-tuning is a critical technique in modern machine learning that leverages transfer learning. Instead of training a model from scratch — which requires massive amounts of data and computational power — developers start with a "foundation model" that already understands general language or visual patterns. By fine-tuning this model on a targeted dataset (such as medical records, legal documents, or a company's specific brand guidelines), the model's weights are slightly adjusted. This results in a highly specialized AI that retains its broad foundational knowledge while excelling at narrow, industry-specific applications with high accuracy.