11 min listen
Visual Illusions Deceiving Neural Networks
FromData Skeptic
ratings:
Length:
34 minutes
Released:
Jan 1, 2021
Format:
Podcast episode
Description
Today on the show we have Adrian Martin, a Postdoctorial researcher from the Univeristy of Pompeu Fabra in Barcelona, Spain. He comes on the show today to discuss his research from the paper “Convolutional Neural Networks can be Decieved by Visual Illusions.” Workes Mentioned in Paper: “Convolutional Neural Networks can be Decieved by Visual Illusions.” by Alexander Gomez-Villa, Adrian Martin, Javier Vazquez-Corral, and Marcelo Bertalmio Examples: Snake Illusions https://www.illusionsindex.org/i/rotating-snakes Twitter: Alex: @alviur Adrian: @adriMartin13 Thanks to our sponsor! Keep your home internet connection safe with Nord VPN! Get 68% off plus a free month at nordvpn.com/dataskeptic (30-day money-back guarantee!)
Released:
Jan 1, 2021
Format:
Podcast episode
Titles in the series (100)
[MINI] type i / type ii errors: In this first mini-episode of the Data Skeptic Podcast, we define and discuss type i and type ii errors (a.k.a. false positives and false negatives). by Data Skeptic