Building Intuition into Adversarial Examples in Deep Learning

#SPS #AI #artificial #intelligence #deep #learning #neural #networks #computer #vision #signal #processing
Share

If you are not an IEEE member but would like to attend, please e-mail Pavel Tcherniaev at paveltc@gmail.com

In recent years, deep neural networks have found wide ranging applications in the general field of AI. However, it has been shown that deep learning suffers from Adversarial Examples which have puzzled AI scientists. For acceptance of deep learning based AI solutions, it is important to understand this intriguing phenomenon and to eliminate it. Furthermore, there has been debate in social media about urgent need to bring rigor to the field of deep learning. Inspired by that, in this talk, we present novel results which explain adversarial examples in Computer Vision and which also pave way for future progress in AI.

  Date and Time

  Location

  Hosts

  Registration


  • Date: 07 Feb 2018
  • Time: 06:30 PM to 09:00 PM
  • All times are (UTC-08:00) Pacific Time (US & Canada)
  • Add_To_Calendar_icon Add Event to Calendar
  • 3600 Juliette Ln
  • Santa Clara, California
  • United States 95054
  • Building: Intel SC12 Auditorium
  • Contact Event Host
  • Starts 22 January 2018 10:00 PM
  • Ends 07 February 2018 06:00 PM
  • All times are (UTC-08:00) Pacific Time (US & Canada)
  • No Admission Charge
  • Menu: IEEE Member - $0, Guest - $5 (Pay at door), Intel Employee - $0 (Badge must be present)

  Speakers

Dr. Simant Dube of AI Winning Solutions

Topic:

Building Intuition into Adversarial Examples in Deep Learning

In recent years, deep neural networks have found wide ranging applications in the general field of AI. However, it has been shown that deep learning suffers from Adversarial Examples which have puzzled AI scientists. For acceptance of deep learning based AI solutions, it is important to understand this intriguing phenomenon and to eliminate it. Furthermore, there has been debate in social media about urgent need to bring rigor to the field of deep learning. Inspired by that, in this talk, we present novel results which explain adversarial examples in Computer Vision and which also pave way for future progress in AI.

Biography:

Dr. Simant Dube is a computer scientist and engineer with interests in Machine Learning, Computer Vision, AI and Data Science. Most recently he worked as Senior Principal Engineer at Bossa Nova Robotics and as Faculty Member at New College of Florida, the honors college of Florida. He has worked in industry building successful products, such as automatic analysis of protein crystal images, statistical analysis of copy number variation in biotechnology, firefly technology to recognize millions of products with smartphone camera, automatic analysis of images of aisles of retail supermarkets, and others. Currently, he is working with startup incubators and academic institutes in the field of AI.