Webinar Overview:

Deep neural networks are capable of amazing levels of representation power resulting in state-of-the-art accuracy in areas such as computer vision, speech recognition, natural language processing, and various data analytic domains. Deep networks require large amounts of computation to train. Intel is optimizing popular frameworks such as Caffe*, TensorFlow*, Theano*, and others to significantly improve performance reducing the overall time to train on a single node. Intel is also enhancing multi-node distributed training capabilities to these frameworks.

This webinar will briefly recap our Deep Learning 101 lecture, and then explore the topics of:

  • Multi-layer perceptrons
  • Convolutional neural networks
  • Recurrent neural networks
  • Cost functions
  • Backpropogation
Required Fields (*)

I am a Student or Professor.

By submitting this form, you are confirming you are an adult 18 years or older and you agree to Intel contacting you with marketing-related emails or by telephone. You may unsubscribe at any time. Intel's web sites and communications are subject to our Privacy Notice and Terms of Use.


Andres Rodriguez, PhD

Deep Learning Solutions Architect
Intel Corporation

Andres Rodriguez is a deep learning solutions architect within Intel’s Data Center Group. He has worked in machine learning for over 12 years and received his PhD for his work in machine learning.