Easily Fooling Deep Neural Networks
Data Skeptic16 Tammi 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.

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(601)

Bioinspired Engineering

Bioinspired Engineering

Brian Taylor shares his research on magnetoreception. Animals like birds and sea turtles use magnetoreception to use the Earth's magnetic field for navigation, but it's not a sense that's well underst...

14 Touko 202438min

Modelling Evolution

Modelling Evolution

Modeling evolutionary processes goes way beyond the Hardy-Weinberg Equilibrium we all learned in biology class. Natural selection comes from many sources like resources availability, mate preferences,...

9 Touko 202441min

Behavioral Genetics

Behavioral Genetics

It's almost impossible to think about animal behavior without thinking of dogs! Our canine friends are a subspecies of wolf that has been co-evolving with us for tens of thousands of years. The transi...

30 Huhti 202447min

Signal in the Noise

Signal in the Noise

In this episode, we are joined by Barbara Webb and Anna Hadjitofi. Barbara runs the Insect Robotics lab at the University of Edinburgh, and Anna is a PhD student at the School of Informatics at the un...

25 Huhti 202441min

Pose Tracking

Pose Tracking

Many researchers and students have painstakingly labeled precise details about the body positions of the creatures they study. Can AI be used for this labeling? Of course it can! Today's episode discu...

16 Huhti 202450min

Modeling Group Behavior

Modeling Group Behavior

Our guest in this episode is Sebastien Motsch, an assistant professor at Arizona State University, working in the School of Mathematical and Statistical Science. He works on modeling self-organized bi...

8 Huhti 202440min

Advances in Data Loggers

Advances in Data Loggers

Our guest in this episode is Ryan Hanscom. Ryan is a Ph.D. candidate in a joint doctoral evolution program at San Diego State University and the University of California, Riverside. He is a terrestria...

25 Maalis 202435min

What You Know About Intelligence is Wrong (fixed)

What You Know About Intelligence is Wrong (fixed)

We are joined by Hank Schlinger, a professor of psychology at California State University, Los Angeles. His research revolves around theoretical issues in psychology and behavioral analysis.  Hank est...

20 Maalis 202441min

Suosittua kategoriassa Tiede

rss-mita-tulisi-tietaa
rss-poliisin-mieli
tiedekulma-podcast
rss-duodecim-lehti
menologeja-tutkimusmatka-vaihdevuosiin
docemilia
rss-astetta-parempi-elama-podcast
rss-tiedetta-vai-tarinaa
rss-lapsuuden-rakentajat-podcast
utelias-mieli
sotataidon-ytimessa
radio-antro
filocast-filosofian-perusteet
rss-ranskaa-raakana
rss-kasvatuspsykologiaa-kaikille
rss-sosiopodi