Easily Fooling Deep Neural Networks
Data Skeptic16 Jan 2015

Easily Fooling Deep Neural Networks

My guest this week is Anh Nguyen, a PhD student at the University of Wyoming working in the Evolving AI lab. The episode discusses the paper Deep Neural Networks are Easily Fooled [pdf] by Anh Nguyen, Jason Yosinski, and Jeff Clune. It describes a process for creating images that a trained deep neural network will mis-classify. If you have a deep neural network that has been trained to recognize certain types of objects in images, these "fooling" images can be constructed in a way which the network will mis-classify them. To a human observer, these fooling images often have no resemblance whatsoever to the assigned label. Previous work had shown that some images which appear to be unrecognizable white noise images to us can fool a deep neural network. This paper extends the result showing abstract images of shapes and colors, many of which have form (just not the one the network thinks) can also trick the network.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(601)

ML Ops in Production

ML Ops in Production

Moses Guttman from Clear ML joins us to share insights about how organizations leveraging machine learning keep their programs on track.  While many parallels exist between the software development li...

6 Okt 202241min

Ad Network Tomography

Ad Network Tomography

Data sharing in the ad tech space has largely been a black box system. While it is obvious the data is being collected, the data sharing process is obscure to users. On the show today, Maaz Bin Musa a...

3 Okt 202235min

First Party Tracking Cookies

First Party Tracking Cookies

When you accept cookies on a website, you cannot tell whether the cookies are used for tracking your personal data or not. Shaoor Munir's machine learning model does that. On the show today, the Ph.D ...

26 Sep 202235min

The Harms of Targeted Weight Loss Ads

The Harms of Targeted Weight Loss Ads

Liza Gak, a Ph.D. student at UC Berkeley, joins us to discuss her research on harmful weight loss advertising. She discussed how weight loss ads are not fact-checked, and how they typically target the...

19 Sep 202234min

Podcast Advertising

Podcast Advertising

Growing your podcast to the point of monetization is not a walk in the park. Today, Rob Walch, the VP of Podcast Relations at Libsyn talks about podcast advertising. He discussed how advertising works...

12 Sep 202235min

Fairness in e-Commerce Search

Fairness in e-Commerce Search

When we search for products in e-commerce stores, we do not care what goes on under the hood to generate the results. However, there may be an intentional algorithmic effort to gravitate us toward a p...

5 Sep 202240min

Fraudulent Amazon Reviewers

Fraudulent Amazon Reviewers

Chances are that you have bought a product online majorly because of the reviews you saw. Unfortunately, not all reviews are genuine. Today, Rajvardhan Oak shares some insight from his research on fra...

29 Aug 202241min

Ad Targeting in Amazon Smart Speakers

Ad Targeting in Amazon Smart Speakers

While we give attention to textual data on the web, many do not know the unique power of echo interactions with smart devices for ad targeting. Today, our guest, Umar Iqbal joins us to discuss his stu...

22 Aug 202232min

Populært innen Vitenskap

fastlegen
jss
tingenes-tilstand
forskningno
rekommandert
rss-paradigmepodden
villmarksliv
sinnsyn
rss-zahid-ali-hjelper-deg
vett-og-vitenskap-med-gaute-einevoll
kvinnehelsepodden
rss-inn-til-kjernen-med-sunniva-rose
nordnorsk-historie
nevropodden
tidlose-historier
liberal-halvtime
fjellsportpodden
rss-overskuddsliv
grunnstoffene
rss-rekommandert