Growing Cellular Automata

10 days ago

Differentiable Self-Organisation: Cellular Automata model of Morphogenesis.

Visualizing the Impact of Feature Attribution Baselines

about 1 month ago

Exploring the baseline input hyperparameter, and how it impacts interpretations of neural...

Computing Receptive Fields of Convolutional Neural Networks

4 months ago

Detailed derivations and open-source code to analyze the receptive fields of convnets.

The Paths Perspective on Value Learning

about 50 years ago

A closer look at how Temporal Difference Learning merges paths of experience...

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Adversarial Examples are Just Bugs, Too

about 50 years ago

Refining the source of adversarial examples

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Adversarial Example Researchers Need to Expand What is Meant by 'Robustness'

about 50 years ago

The main hypothesis in Ilyas et al. (2019) happens to be a...

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Two Examples of Useful, Non-Robust Features

about 50 years ago

An example project using webpack and svelte-loader and ejs to inline SVGs

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Discussion and Author Responses

about 50 years ago

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Adversarially Robust Neural Style Transfer

about 50 years ago

An experiment showing adversarial robustness makes neural style transfer work on a...

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Robust Feature Leakage

about 50 years ago

An example project using webpack and svelte-loader and ejs to inline SVGs

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features'

about 50 years ago

Six comments from the community and responses from the original authors

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Learning from Incorrectly Labeled Data

about 50 years ago

Section 3.2 of Ilyas et al. (2019) shows that training a model...