Theoretical Motivations for Deep Learning
Posted by Armando Brito Mendes | Filed under lições
clicar na imagem para seguir o link
Uma boa introdução ao Deep Learning uma nova técnica de machine learning.
This post is based on the lecture “Deep Learning: Theoretical Motivations” given by Dr. Yoshua Bengio at Deep Learning Summer School, Montreal 2015. I highly recommend the lecture for a deeper understanding of the topic.
Deep learning is a branch of machine learning algorithms based on learning multiple levels of representation. The multiple levels of representation corresponds to multiple levels of abstraction. This post explores the idea that if we can successfully learn multiple levels of representation then we can generalize well.
Tags: data mining, machine learning
Comments are closed.
