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)

Privacy Preference Signals

Privacy Preference Signals

Have you ever wondered what goes on under the hood when you accept a website's cookies? Today, Maximilian Hils, a PhD student in Computer Science, at the University of Innsbruck, Austria, dissects the...

4 Jul 202233min

Neural Architecture Search for CTR Prediction

Neural Architecture Search for CTR Prediction

Ravi Krishna joins us today to talk about his recent work on a differentiable NAS framework for ads CTR prediction. He discussed what CTR prediction is about and why his NAS framework helps in buildin...

27 Jun 202228min

Algorithmic PPC Management

Algorithmic PPC Management

Effectively managing a large budget of pay per click advertising demands software solutions. When spending multi-million dollar budgets on hundreds of thousands of keywords, an effective algorithmic s...

21 Jun 202243min

Data Skeptic: Ad Tech

Data Skeptic: Ad Tech

Increasingly, people get most if not all of the information they consume online. Alongside the web sites, videos, apps, and other destinations, we're consistently served advertisements alongside the o...

18 Jun 202242min

The Reliability of Mobile Phone Data

The Reliability of Mobile Phone Data

Our mobile phones generate an incredible amount of data inbound and outbound. In today's episode, Nishant Kishore, a PhD graduate of Harvard University in Infectious Disease Epidemiology, explains how...

13 Jun 202249min

Haywire Algorithms

Haywire Algorithms

The pandemic changed how we lived. And this had a ripple effect on the performance of machine learning models. Ravi Parikh joins us today to discuss how the pandemic has affected the performance of ma...

6 Jun 202233min

School Reopening Analysis

School Reopening Analysis

Carly Lupton-Smith joins us today to speak about her research which investigated the consistency between household and county measures of school reopening. Carly is a doctoral researcher in Biostatist...

30 Mai 202233min

Modern Data Stacks

Modern Data Stacks

Today, we are joined by Alexander Thor, a Product Manager at Vizlib, makers of Astrato. Astrato is a data analytics and business intelligence tool built on the cloud and for the cloud. Alexander discu...

26 Mai 202234min

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