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.

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(601)

Black Friday

Black Friday

The retail holiday "black Friday" occurs the day after Thanksgiving in the United States. It's dubbed this because many retail companies spend the first 10 months of the year running at a loss (in the...

26 Nov 202144min

Aligning Time Series on Incomparable Spaces

Aligning Time Series on Incomparable Spaces

Alex Terenin, Postdoctoral Research Associate at the University of Cambridge, joins us today to talk about his work "Aligning Time Series on Incomparable Spaces."

22 Nov 202133min

Comparing Time Series with HCTSA

Comparing Time Series with HCTSA

Today we are joined again by Ben Fulcher, leader of the Dynamics and Neural Systems Group at the University of Sydney in Australia, to talk about hctsa, a software package for running highly comparati...

15 Nov 202142min

Change Point Detection Algorithms

Change Point Detection Algorithms

Gerrit van den Burg, Postdoctoral Researcher at The Alan Turing Institute, joins us today to discuss his work "An Evaluation of Change Point Detection Algorithms."

8 Nov 202130min

Time Series for Good

Time Series for Good

Bahman Rostami-Tabar, Senior Lecturer in Management Science at Cardiff University, joins us today to talk about his work "Forecasting and its Beneficiaries."

1 Nov 202137min

Long Term Time Series Forecasting

Long Term Time Series Forecasting

Alex Mallen, Computer Science student at the University of Washington, and Henning Lange, a Postdoctoral Scholar in Applied Math at the University of Washington, join us today to share their work "Dee...

25 Okt 202137min

Fast and Frugal Time Series Forecasting

Fast and Frugal Time Series Forecasting

Fotios Petropoulos, Professor of Management Science at the University of Bath in The U.K., joins us today to talk about his work "Fast and Frugal Time Series Forecasting."

17 Okt 202137min

Causal Inference in Educational Systems

Causal Inference in Educational Systems

Manie Tadayon, a PhD graduate from the ECE department at University of California, Los Angeles, joins us today to talk about his work "Comparative Analysis of the Hidden Markov Model and LSTM: A Simul...

11 Okt 202141min

Populärt inom Vetenskap

allt-du-velat-veta
dumma-manniskor
p3-dystopia
rss-ufobortom-rimligt-tvivel
ufo-sverige
kapitalet-en-podd-om-ekonomi
sexet
medicinvetarna
svd-nyhetsartiklar
rss-vetenskapsradion
hacka-livet
rss-vetenskapsradion-2
paranormalt-med-caroline-giertz
det-morka-psyket
ufo-sverige-2
rss-spraket
halsorevolutionen
rss-klotet
dumforklarat
ideer-som-forandrar-varlden