Meta-learning is a broad machine learning term. It has a number of meanings, but it generally entails utilizing metadata for a specific problem in order to solve it. Its applications range from solving a problem more efficiently, to designing entirely new learning algorithms. It is a growing research field that has recently yielded impressive results by designing novel deep learning architectures.
Meta-learning
Stacking
Stacking is a form of meta-learning. The main idea is that we use base learners in order to generate metadata for the problem's dataset and then utilize another learner called a meta-learner, in order to process the metadata. Base learners are considered to be level 0 learners, while the meta learner is...
