LM101-029: How to Modernize Deep Learning with Rectilinear units, Convolutional Nets, and Max-Pooling

05.25.2015 - By Learning Machines 101

Download our free app to listen on your phone

This podcast discusses talks, papers, and ideas presented at the recent International Conference on Learning Representations 2015 which was followed by the Artificial Intelligence in Statistics 2015 Conference in San Diego. Specifically, commonly used techniques shared by many successful deep learning algorithms such as: rectilinear units, convolutional filters, and max-pooling are discussed. For more details please visit our website at: www.learningmachines101.com! 

More episodes from Learning Machines 101