Software Development

Zoom In: An Introduction to Circuits

By studying the connections between neurons, we can find meaningful algorithms in the weights of neural networks.

Mar 10, 2020 960 views

Growing Neural Cellular Automata

Training an end-to-end differentiable, self-organising cellular automata model of morphogenesis, able to both grow and regenerate specific patterns.

Feb 11, 2020 394 views

Visualizing the Impact of Feature Attribution Baselines

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

Jan 10, 2020 602 views

Computing Receptive Fields of Convolutional Neural Networks

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

Nov 04, 2019 885 views

The Paths Perspective on Value Learning

A closer look at how Temporal Difference Learning merges paths of experience for greater statistical efficiency

Sep 30, 2019 989 views

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

This article is part of a discussion of the Ilyas et al. paper “Adversarial examples are not bugs, they are features”. You can learn more in the main discussion article . We want to thank all the comm...

Aug 06, 2019 456 views

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

Section 3.2 of Ilyas et al. (2019) shows that training a model on only adversarial errors leads to non-trivial generalization on the original test set. We show that these experiments are a specific ca...

Aug 06, 2019 521 views

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

Refining the source of adversarial examples

Aug 06, 2019 608 views

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

An experiment showing adversarial robustness makes neural style transfer work on a non-VGG architecture

Aug 06, 2019 693 views

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

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

Aug 06, 2019 927 views

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

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

Aug 06, 2019 959 views

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

The main hypothesis in Ilyas et al. (2019) happens to be a special case of a more general principle that is commonly accepted in the robustness to distributional shift literature

Aug 06, 2019 346 views

Open Questions about Generative Adversarial Networks

What we'd like to find out about GANs that we don't know yet.

Apr 09, 2019 876 views

A Visual Exploration of Gaussian Processes

How to turn a collection of small building blocks into a versatile tool for solving regression problems.

Apr 02, 2019 803 views

Visualizing memorization in RNNs

Inspecting gradient magnitudes in context can be a powerful tool to see when recurrent units use short-term or long-term contextual understanding.

Mar 25, 2019 601 views

Activation Atlas

By using feature inversion to visualize millions of activations from an image classification network, we create an explorable activation atlas of features the network has learned and what concepts it ...

Mar 06, 2019 808 views