Gradient agreement as an optimization objective for meta-learning
The gradient agreement algorithm is an interesting and recently introduced algorithm that acts as an enhancement to meta learning algorithms.
The gradient agreement algorithm is an interesting and recently introduced algorithm that acts as an enhancement to meta learning algorithms.
MAML is pretty good at finding the right initial parameter. In this post, we will see how can we use MAML in the supervised learning setting.
We explore how model agnostic meta learning (MAML) works in detail in this post. We will learn how MAML finds the optimal paramater.
We will learn about Model Agnostic Meta Learning (MAML) which is one of the recently introduced and most popularly used meta learning algorithms.