Abstract

In this talk, Prof. Mello introduces the main concerns and motivations to the Statistical Learning Theory based on his recently published book (under the same title of this talk) in conjunction with Prof. Moacir Antonelli Ponti, both from the University of São Paulo, ICMC, São Carlos, Brazil. The Statistical Learning Theory provides the theoretical foundations to supervised learning, helping to understand the complexity of algorithm biases, necessary sample sizes to ensure learning conditions and most specially the bounds to ensure results on never seen examples out of models build from training sets.

Short Bio

Rodrigo Mello is currently a visiting professor at Télécom ParisTech, Paris, France and an associate professor at the Institute of Mathematical and Computer Sciences at the Department of Computer Science at the University of São Paulo, São Carlos, Brazil. He completed his PhD at the University of São Paulo in 2003. His research interests include theoretical learning tests for supervised and unsupervised scenarios, the concepts of statistical learning theory, machine learning, applications in dynamic systems, series analysis and data streams.

About Talks@DCC 

The mission of the Talks@DCC seminars is to bring together researchers and students, to foster discussions and promote scientific awareness and collaboration.

Participate: attend and propose your talk.