Menu
Transfer learning is a machine learning technique that uses a previously trained model as the starting point for a new, yet related model. Reusing a model saves compute time and helps manage model accuracy.
The most common transfer learning techniques are feature extraction and fine-tuning. The techniques differ in how the base layer is treated. Feature extraction freezes the base layer; fine-tuning adjusts the base layer.
Often the best strategy for transfer learning is to start with a proven architecture for your network. When selecting a model, consider the following questions.
How similar is the dataset in terms of categories? (For example, dogs versus cats.)
How similar is the type of model architecture? (For example, ResNet* and edges.)
How similar is the type of task? (For example, image classification versus object detection.)
JA Talents is a Virtual Career Hub that aims to boost youth employability by offering a variety of services provided by the JA Network.
