Christian Wolf·Mar 31Claude decreased the value of papers and killed peer reviewFor years, centuries, the value of a paper was somewhat easy to determine: does the scientific community gain insights from the research…
Christian Wolf·Jan 6Creating 3D Figures for CV/ML papers with BlenderI have been asked how I created the 3D Figures from some of our papers like these:
Christian Wolf·Mar 21, 2021Links between literature on addressing transformer complexity and work on recurrent neural worksThis post addresses some similarities in the ways the Deep field addressed two seemingly different problems, namely A) recent work on…
Christian Wolf·Nov 30, 2020Cow-Sharks: exploring the Shape vs. Texture biases in Deep Neural NetworksThe context to this post are recent papers providing evidence that prediction performance of deep networks trained for image…
Christian Wolf·Oct 5, 2020What 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…A response icon2A response icon2
Christian Wolf·Oct 6, 2018Generalization and random labelsCaveat: I wrote this story initially on Dec. 21st, 2016, but moved it to medium in Oct. 2018.
