Meta-Learning and Automatic Machine Learning
https://zoom.us/j/98479811312?pwd=QXJhVmJ5YSs5dW1uWGExcEVrb21OUT09
Meeting ID: 984 7981 1312
Passcode: 369820
Computer Science Department - DC/CCE
Universidade Estadual de Londrina - UEL
Title: Meta-Learning and Automatic Machine Learning
Abstract
In the last decades, machine learning algorithms could impact vast plural areas of knowledge, creating new challenges to democratize their usage. Selecting and tuning algorithms need to be performed by the vastest users' background. Facing these issues, Meta-learning, or learning to learn, is the science of systematically observing how different machine-learning approaches perform on a wide range of learning tasks and then learning from this experience or meta-data to learn new tasks much faster than otherwise possible. In recent years, Meta-learning has been increasing in importance and arose as an active field of research has developed around automated machine learning(AutoML).
Referente: Paolo Ceravolo