🔬 Research
Distill.pub
36 min read
Curve Detectors
Part one of a three part deep dive into the curve neuron family.
Latest AI News & Research
638 articles
🔬 Research
Distill.pub
29 min read
Exploring Bayesian Optimization
How to tune hyperparameters for your machine learning model using Bayesian optimization.
🔬 Research
Distill.pub
17 min read
An Overview of Early Vision in InceptionV1
An overview of all the neurons in the first five layers of InceptionV1, organized into a taxonomy of 'neuron groups.'
🔬 Research
Distill.pub
42 min read
Visualizing Neural Networks with the Grand Tour
By focusing on linear dimensionality reduction, we show how to visualize many dynamic phenomena in neural networks.
🔬 Research
Distill.pub
5 min read
Thread: Circuits
What can we learn if we invest heavily in reverse engineering a single neural network?
🔬 Research
Distill.pub
42 min read
Zoom In: An Introduction to Circuits
By studying the connections between neurons, we can find meaningful algorithms in the weights of neural networks.
🔬 Research
Distill.pub
24 min read
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.
🔬 Research
Distill.pub
34 min read
Visualizing the Impact of Feature Attribution Baselines
Exploring the baseline input hyperparameter, and how it impacts interpretations of neural network behavior.
🔬 Research
Distill.pub
27 min read
Computing Receptive Fields of Convolutional Neural Networks
Detailed derivations and open-source code to analyze the receptive fields of convnets.
🔬 Research
Distill.pub
17 min read
The Paths Perspective on Value Learning
A closer look at how Temporal Difference Learning merges paths of experience for greater statistical efficiency
🔬 Research
Distill.pub
9 min read
A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features'
Six comments from the community and responses from the original authors
🔬 Research
Distill.pub
9 min read
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
🔬 Research
Distill.pub
6 min read
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
🔬 Research
Distill.pub
6 min read
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