Zeroing In On What Makes Adversarial Examples Possible Linear Digressions podcast

Over 20 million podcasts, powered by

Artwork

Data Science Science Data Linear Digress Ben Jaffe and Katie Malone Ben Jaffe Katie Malone Tech Machining Learn

Content provided by Ben Jaffe and Katie Malone, Ben Jaffe, and Katie Malone. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Ben Jaffe and Katie Malone, Ben Jaffe, and Katie Malone or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.

Linear Digressions « »
Zeroing in on what makes adversarial examples possible

6y ago 22:51

Share

MP3•Episode home

Content provided by Ben Jaffe and Katie Malone, Ben Jaffe, and Katie Malone. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Ben Jaffe and Katie Malone, Ben Jaffe, and Katie Malone or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.

Adversarial examples are really, really weird: pictures of penguins that get classified with high certainty by machine learning algorithms as drumsets, or random noise labeled as pandas, or any one of an infinite number of mistakes in labeling data that humans would never make but computers make with joyous abandon. What gives? A compelling new argument makes the case that it’s not the algorithms so much as the features in the datasets that holds the clue. This week’s episode goes through several papers pushing our collective understanding of adversarial examples, and giving us clues to what makes these counterintuitive cases possible. Relevant links: https://arxiv.org/pdf/1905.02175.pdf https://arxiv.org/pdf/1805.12152.pdf https://distill.pub/2019/advex-bugs-discussion/ https://arxiv.org/pdf/1911.02508.pdf

… continue reading

293 episodes

#Data Science #Science #Data #Linear #Digress #Ben Jaffe and Katie Malone #Ben Jaffe #Katie Malone #Tech #Machining #Learn

Artwork

Zeroing in on what makes adversarial examples possible

Linear Digressions

1,448 subscribers

published 6y ago

Share

MP3•Episode home

Content provided by Ben Jaffe and Katie Malone, Ben Jaffe, and Katie Malone. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Ben Jaffe and Katie Malone, Ben Jaffe, and Katie Malone or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.

Adversarial examples are really, really weird: pictures of penguins that get classified with high certainty by machine learning algorithms as drumsets, or random noise labeled as pandas, or any one of an infinite number of mistakes in labeling data that humans would never make but computers make with joyous abandon. What gives? A compelling new argument makes the case that it’s not the algorithms so much as the features in the datasets that holds the clue. This week’s episode goes through several papers pushing our collective understanding of adversarial examples, and giving us clues to what makes these counterintuitive cases possible. Relevant links: https://arxiv.org/pdf/1905.02175.pdf https://arxiv.org/pdf/1805.12152.pdf https://distill.pub/2019/advex-bugs-discussion/ https://arxiv.org/pdf/1911.02508.pdf

… continue reading

293 episodes

#Data Science #Science #Data #Linear #Digress #Ben Jaffe and Katie Malone #Ben Jaffe #Katie Malone #Tech #Machining #Learn

All episodes

×

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

Listen to 500+ topics

Help/FAQ | Advertise with Us

Arts|Business|Comedy|Economics|Entertainment|News|Politics|Religion

Science|Soccer|Sports|Storytelling|Technology|True Crime

Copyright 2025 | Privacy Policy | Terms of Service | | Copyright

Listen to this show while you explore