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)

Fault Tolerant Distributed Gradient Descent

Fault Tolerant Distributed Gradient Descent

Nirupam Gupta, a Computer Science Post Doctoral Researcher at EDFL University in Switzerland, joins us today to discuss his work "Byzantine Fault-Tolerance in Peer-to-Peer Distributed Gradient-Descent...

22 Feb 202136min

Decentralized Information Gathering

Decentralized Information Gathering

Mikko Lauri, Post Doctoral researcher at the University of Hamburg, Germany, comes on the show today to discuss the work Information Gathering in Decentralized POMDPs by Policy Graph Improvements. Fol...

15 Feb 202132min

Leaderless Consensus

Leaderless Consensus

Balaji Arun, a PhD Student in the Systems of Software Research Group at Virginia Tech, joins us today to discuss his research of distributed systems through the paper "Taming the Contention in Consens...

5 Feb 202127min

Automatic Summarization

Automatic Summarization

Maartje ter Hoeve, PhD Student at the University of Amsterdam, joins us today to discuss her research in automated summarization through the paper "What Makes a Good Summary? Reconsidering the Focus o...

29 Jan 202127min

Gerrymandering

Gerrymandering

Brian Brubach, Assistant Professor in the Computer Science Department at Wellesley College, joins us today to discuss his work "Meddling Metrics: the Effects of Measuring and Constraining Partisan Ger...

22 Jan 202134min

Even Cooperative Chess is Hard

Even Cooperative Chess is Hard

Aside from victory questions like "can black force a checkmate on white in 5 moves?" many novel questions can be asked about a game of chess. Some questions are trivial (e.g. "How many pieces does whi...

15 Jan 202123min

Consecutive Votes in Paxos

Consecutive Votes in Paxos

Eil Goldweber, a graduate student at the University of Michigan, comes on today to share his work in applying formal verification to systems and a modification to the Paxos protocol discussed in the p...

11 Jan 202130min

Visual Illusions Deceiving Neural Networks

Visual Illusions Deceiving Neural Networks

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 "Convolut...

1 Jan 202133min

Populært innen Vitenskap

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