Transfer Learning
Quick Answer
Transfer learning is the practice of taking a model trained for one task and adapting it to a related task, saving time, data and compute. Fine-tuning a pre-trained language model on your own data is the most common contemporary example.
In Depth
What Transfer Learning really means
Transfer learning works because many useful features — edges in images, syntax in language — are shared across tasks. Starting from a strong general-purpose model and specialising it is typically far more efficient than training from scratch.
Considerations include choosing the right base model (licensed for commercial use, appropriate architecture, acceptable risk profile), freezing versus fine-tuning layers, and managing the ongoing relationship with the upstream model provider.
Why It Matters
Business relevance for UK organisations
For most UK businesses, transfer learning is the only realistic path to high-quality custom AI. Training large models from scratch is economically out of reach; adapting pre-trained ones is not.
Real-world example
How this shows up in practice
An Edinburgh climate-tech startup used transfer learning to adapt a satellite-image model to detect illegal forestry in a new region using just 3,000 labelled examples.
Related Terms
Continue exploring
Fine-tuning
Fine-tuning is the process of further training a pre-trained model on a smaller, task-specific dataset so that it specialises in a particular domain, tone or set of behaviours. It sits between using a base model as-is and training a new model from scratch.
BasicsDeep Learning
Deep Learning is a branch of machine learning that uses multi-layered neural networks to learn highly complex patterns directly from raw data such as images, audio and text, without the need for hand-crafted feature engineering.
BasicsTraining Data
Training data is the dataset used to teach a machine learning model the patterns it needs to perform its task. The quality, quantity, diversity and recency of training data directly determine how accurate and fair the resulting model will be.
BasicsMachine Learning
Machine Learning (ML) is a subfield of AI in which systems learn patterns from historical data rather than following explicitly programmed rules, enabling them to make predictions or decisions on new, unseen data as conditions evolve.