You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
17 lines
637 B
17 lines
637 B
---
|
|
id: 4334
|
|
title: 'Tensorflow, is there really no spoon ?'
|
|
language: English
|
|
complexity: Intermédiaire
|
|
tags:
|
|
- Big Data / ML / AI
|
|
videoId: 4QIjIoHP0x4
|
|
speakers:
|
|
- tiffany_souterre
|
|
talkType: Conférence
|
|
|
|
---
|
|
|
|
With the advance of Deep learning, Image recognition is everywhere! But like all technologies, it has its flaws. It is indeed possible to fool neural network models used for critical applications such as self-driving cars, drones, security cameras... Together, we will see how to generate adversarial images and fool a neural network into seeing something in an image that is not there.
|
|
|
|
No Tensorflow, there is no spoon!
|
|
|