pre-training

{
  "id": "MLC-T-CYB-003224",
  "term": "pre-training",
  "field": "Cybersecurity",
  "definition": "1. In machine learning, a training step that trains a general-purpose model (sometimes called a foundation model) on publicly-available data. Pre-training is often followed by fine-tuning to equip the model with task-specific information.\n\n2. A component of the training stage in which a model learns general patterns, features, and relationships from vast amounts of unlabeled data, such as through self-supervised learning. Pre-training can equip models with knowledge of general features or patterns which may be useful in downstream tasks, and can be followed with additional training or fine-tuning that specializes the model for a specific downstream task.",
  "references": [
    "NIST SP 800-226",
    "NIST AI 100-2e2025",
    "NIST CSRC Glossary"
  ],
  "url": "https://mlchart.com/terminology/cybersecurity/pre-training/"
}