ICML, ‘17

https://arxiv.org/abs/1703.03400

Summary

• MAML is a general and model-agnostic algorithm that can be directly applied to a model trained with gradient descent procedure.
• MAML does not expand the number of learned parameters.
• MAML does not place constraints on the model architecture.

Key words

• Model agnostic
• Fast adaptation
• Optimization based approach
• Learning good model parameters

Prelimiaries

• Common Approaches of Meta-Learning and MAML
• A few terminologies of meta-learning problems

1. Introduction

Goal of ideal artificial agent:

Learning and adapting quickly from only a few examples.

To do so, an agent must..

• Integrate its prior experience with a small amount of new information.
• Avoid overfitting to the new data.

→ Meta-learning has same goals.