Glossary

Learning with a small amount of data; few-shot learning

Artificial intelligence method that enables a model to learn to solve a task using very few examples. Unlike conventional approaches requiring thousands of data sets, low-data learning seeks to mimic the human ability to generalize a decision or prediction, etc., from just a few cases: this makes it useful in fields where data is scarce or expensive to collect.

Transfer learning

Transfer learning involves reusing a model trained on one task to adapt it to another, with little new data. This saves time and resources, as the model has already learned useful representations. For example, a network trained to recognize animals can be adjusted to identify plants by changing only the last few layers.

Biais algorithmique; algorithmic bias...