AI Glossary

The complete dictionary of Artificial Intelligence

162

Optimization technique that calculates gradients with respect to meta-parameters to improve learning performance across tasks.

Features extracted from learning task properties used to improve the model's transfer and adaptation process.

Fundamental concept of meta-learning where the algorithm acquires learning skills that can be transferred to new problems.

Process of optimizing hyperparameters and model architecture to improve meta-learning performance on new tasks.

Primary objective of meta-learning aiming to enable models to adapt to new tasks with minimal data and training time.

Training strategy in meta-learning where each episode simulates a few-shot task with support and query sets.

🔍