Christian Wolf – Medium

Christian Wolf

Links between literature on addressing transformer complexity and work on recurrent neural works

This post addresses some similarities in the ways the Deep field addressed two seemingly different problems, namely A) recent work on…

Mar 21, 2021

Links between literature on addressing transformer complexity and work on recurrent neural works

Mar 21, 2021

Cow-Sharks: exploring the Shape vs. Texture biases in Deep Neural Networks

The context to this post are recent papers providing evidence that prediction performance of deep networks trained for image…

Nov 30, 2020

Cow-Sharks: exploring the Shape vs. Texture biases in Deep Neural Networks

Nov 30, 2020

What is translation equivariance, and why do we use convolutions to get it?

Multi-layer Perceptrons (MLPs) are standard neural networks with fully connected layers, where each input unit is connected with each…

Oct 5, 2020

What is translation equivariance, and why do we use convolutions to get it?

Oct 5, 2020

Before and after Deep Learning

Oct 6, 2018

Before and after Deep Learning

Oct 6, 2018

Generalization and random labels

Caveat: I wrote this story initially on Dec. 21st, 2016, but moved it to medium in Oct. 2018.

Oct 6, 2018

Generalization and random labels

Oct 6, 2018

Christian Wolf

Christian Wolf

Scientist in Machine/Deep Learning, AI, Robotics, Computer Vision. AI research chair @INSAdeLyon. Austrian living in France. 3 person family, 3 nationalities.

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams