logo
episode-header-image
Jan 2021
33m 43s

Visual Illusions Deceiving Neural Networ...

Kyle Polich
About this episode

Today on the show we have Adrian Martin, a Post-doctoral researcher from the University of Pompeu Fabra in Barcelona, Spain. He comes on the show today to discuss his research from the paper “Convolutional Neural Networks can be Deceived by Visual Illusions.”

Works 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!)

Up next
Jul 6
The Network Diversion Problem
In this episode, Professor Pål Grønås Drange from the University of Bergen, introduces the field of Parameterized Complexity - a powerful framework for tackling hard computational problems by focusing on specific structural aspects of the input. This framework allows researchers ... Show More
46m 14s
Jun 28
Complex Dynamic in Networks
In this episode, we learn why simply analyzing the structure of a network is not enough, and how the dynamics - the actual mechanisms of interaction between components - can drastically change how information or influence spreads. Our guest, Professor Baruch Barzel of Bar-Ilan Un ... Show More
56 m
Jun 22
Github Network Analysis
In this episode we'll discuss how to use Github data as a network to extract insights about teamwork. Our guest, Gabriel Ramirez, manager of the notifications team at GitHub, will show how to apply network analysis to better understand and improve collaboration within his enginee ... Show More
36m 46s
Recommended Episodes
Apr 2023
Olaf Sporns on Network Neuroscience
The intersection between cutting-edge neuroscience and the emerging field of network science has been growing tremendously over the past decade. Olaf Sporns, editor of Network Neuroscience, and Distinguished Professor, Provost Professor of Department of Psychological and Brain Sc ... Show More
13m 5s
Feb 2021
Introducing “Sudhir Breaks the Internet”
Sudhir Venkatesh, a sociologist who has studied crack gangs, sex workers, and gun runners, suddenly found himself working at Facebook, and later at Twitter. Now he’s back from Silicon Valley to explore and explain our overheated digital universe. “Sudhir Breaks the Internet” is a ... Show More
2m 54s
Jul 2021
Internet shutdowns in Latin America
As protests continue in Cuba, so do its internet shutdowns. Anti-government protesters are demonstrating against food shortages, power cuts and coronavirus restrictions. In response Cuban authorities have been shutting down internet connections in an attempt to stop protests. Mea ... Show More
47m 52s
Oct 2019
AI in the browser
We’ve mentioned ML/AI in the browser and in JS a bunch on this show, but we haven’t done a deep dive on the subject… until now! Victor Dibia helps us understand why people are interested in porting models to the browser and how people are using the functionality. We discuss Tenso ... Show More
49m 40s
Sep 2015
Russia's Red Web - Older Entrepreneurs
The 'Red Web': The Internet in Russia is a totalitarian tool but is also a device by which totalitarianism can be resisted. Laurie Taylor talks to Andrei Soldatov, a Moscow based journalist and co-author of a book which explores the Russian government's battle with the future of ... Show More
28m 5s
Nov 2022
The practicalities of releasing models
Recently Chris and Daniel briefly discussed the Open RAIL-M licensing and model releases on Hugging Face. In this episode, Daniel follows up on this topic based on some recent practical experience. Also included is a discussion about graph neural networks, message passing, and tw ... Show More
37m 19s
Oct 2023
Peering Into A.I.’s Black Box + Who’s The Real Techno-Optimist? + Reading Ancient Scrolls With A.I.
A.I. models are black boxes. You input a prompt and the model outputs nearly anything: a sonnet, an image or a legal brief riddled with lies. Today, a look at three ways that researchers are unlocking that black box in hopes of bringing transparency to A.I.Then, Marc Andreessen’s ... Show More
1h 4m
Jan 2024
The world of VPNs
Tech Life does a deep dive into Virtual Private Networks, or VPNs. We find out the countries where they are most in demand. Also in this edition, we learn about video gaming in Iran. And we speak to the teenager in India who invented a device to help people with Alzheimer's, insp ... Show More
27m 17s
Sep 2020
The Livewired Brain with David Eagleman
What does our growing understanding of neuroplasticity reveal about our brains and the future of technology? In this episode of Stuff to Blow Your Mind, Robert chats with neuroscientist David Eagleman about his new book “Livewired: The Inside Story of the Ever-Changing Brain.” Le ... Show More
40m 45s