What components are needed for building learning algorithms that leverage the structure and properties of graphs?
What components are needed for building learning algorithms that leverage the structure and properties of graphs?
distill.pub
All items hosted on this domain, most recent first.
-
-
Understanding the building blocks and design choices of graph neural networks.
Understanding the building blocks and design choices of graph neural networks. -
After five years, Distill will be taking a break.
After five years, Distill will be taking a break. -
Reprogramming Neural CA to exhibit novel behaviour, using adversarial attacks.
Reprogramming Neural CA to exhibit novel behaviour, using adversarial attacks. -
Weights in the final layer of common visual models appear as horizontal bands. We investigate how and why.
Weights in the final layer of common visual models appear as horizontal bands. We investigate how and why. -
When a neural network layer is divided into multiple branches, neurons self-organize into coherent groupings.
When a neural network layer is divided into multiple branches, neurons self-organize into coherent groupings. -
We report the existence of multimodal neurons in artificial neural networks, similar to those found in the human brain.
We report the existence of multimodal neurons in artificial neural networks, similar to those found in the human brain. -
Neural Cellular Automata learn to generate textures, exhibiting surprising properties.
Neural Cellular Automata learn to generate textures, exhibiting surprising properties. -
We present techniques for visualizing, contextualizing, and understanding neural network weights.
We present techniques for visualizing, contextualizing, and understanding neural network weights. -
Reverse engineering the curve detection algorithm from InceptionV1 and reimplementing it from scratch.
Reverse engineering the curve detection algorithm from InceptionV1 and reimplementing it from scratch. -
A family of early-vision neurons reacting to directional transitions from high to low spatial frequency.
A family of early-vision neurons reacting to directional transitions from high to low spatial frequency. -
Neural networks naturally learn many transformed copies of the same feature, connected by symmetric weights.
Neural networks naturally learn many transformed copies of the same feature, connected by symmetric weights. -
With diverse environments, we can analyze, diagnose and edit deep reinforcement learning models using attribution.
With diverse environments, we can analyze, diagnose and edit deep reinforcement learning models using attribution. -
Examining the design of interactive articles by synthesizing theory from disciplines such as education, journalism, and visualization.
Examining the design of interactive articles by synthesizing theory from disciplines such as education, journalism, and visualization. -
Training an end-to-end differentiable, self-organising cellular automata for classifying MNIST digits.
Training an end-to-end differentiable, self-organising cellular automata for classifying MNIST digits. -
A collection of articles and comments with the goal of understanding how to design robust and general purpose self-organizing systems.
A collection of articles and comments with the goal of understanding how to design robust and general purpose self-organizing systems. -
Part one of a three part deep dive into the curve neuron family.
Part one of a three part deep dive into the curve neuron family. -
How to tune hyperparameters for your machine learning model using Bayesian optimization.
How to tune hyperparameters for your machine learning model using Bayesian optimization. -
An overview of all the neurons in the first five layers of InceptionV1, organized into a taxonomy of 'neuron groups.'
An overview of all the neurons in the first five layers of InceptionV1, organized into a taxonomy of 'neuron groups.' -
By focusing on linear dimensionality reduction, we show how to visualize many dynamic phenomena in neural networks.
By focusing on linear dimensionality reduction, we show how to visualize many dynamic phenomena in neural networks. -
By studying the connections between neurons, we can find meaningful algorithms in the weights of neural networks.
By studying the connections between neurons, we can find meaningful algorithms in the weights of neural networks. -
What can we learn if we invest heavily in reverse engineering a single neural network?
What can we learn if we invest heavily in reverse engineering a single neural network? -
Training an end-to-end differentiable, self-organising cellular automata model of morphogenesis, able to both grow and regenerate specific patterns.
Training an end-to-end differentiable, self-organising cellular automata model of morphogenesis, able to both grow and regenerate specific patterns. -
Exploring the baseline input hyperparameter, and how it impacts interpretations of neural network behavior.
Exploring the baseline input hyperparameter, and how it impacts interpretations of neural network behavior. -
Detailed derivations and open-source code to analyze the receptive fields of convnets.
Detailed derivations and open-source code to analyze the receptive fields of convnets. -
A closer look at how Temporal Difference Learning merges paths of experience for greater statistical efficiency
A closer look at how Temporal Difference Learning merges paths of experience for greater statistical efficiency -
No full content extracted yet.
Extracting… -
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 case of learning from errors.
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 case of learning from errors. -
Refining the source of adversarial examples
Refining the source of adversarial examples -
An experiment showing adversarial robustness makes neural style transfer work on a non-VGG architecture
An experiment showing adversarial robustness makes neural style transfer work on a non-VGG architecture -
An example project using webpack and svelte-loader and ejs to inline SVGs
An example project using webpack and svelte-loader and ejs to inline SVGs -
An example project using webpack and svelte-loader and ejs to inline SVGs
An example project using webpack and svelte-loader and ejs to inline SVGs -
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
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 -
Six comments from the community and responses from the original authors
Six comments from the community and responses from the original authors -
What we'd like to find out about GANs that we don't know yet.
What we'd like to find out about GANs that we don't know yet. -
How to turn a collection of small building blocks into a versatile tool for solving regression problems.
How to turn a collection of small building blocks into a versatile tool for solving regression problems. -
Inspecting gradient magnitudes in context can be a powerful tool to see when recurrent units use short-term or long-term contextual understanding.
Inspecting gradient magnitudes in context can be a powerful tool to see when recurrent units use short-term or long-term contextual understanding. -
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 typically represents.
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 typically represents. -
If we want to train AI to do what humans want, we need to study humans.
If we want to train AI to do what humans want, we need to study humans. -
An Update from the Editorial Team
An Update from the Editorial Team -
A powerful, under-explored tool for neural network visualizations and art.
A powerful, under-explored tool for neural network visualizations and art. -
A simple and surprisingly effective family of conditioning mechanisms.
A simple and surprisingly effective family of conditioning mechanisms. -
Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them -- and the rich structure of this combinatorial space.
Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them -- and the rich structure of this combinatorial space. -
By creating user interfaces which let us work with the representations inside machine learning models, we can give people new tools for reasoning.
By creating user interfaces which let us work with the representations inside machine learning models, we can give people new tools for reasoning. -
A visual guide to Connectionist Temporal Classification, an algorithm used to train deep neural networks in speech recognition, handwriting recognition and other sequence problems.
A visual guide to Connectionist Temporal Classification, an algorithm used to train deep neural networks in speech recognition, handwriting recognition and other sequence problems. -
How neural networks build up their understanding of images
How neural networks build up their understanding of images -
We often think of optimization with momentum as a ball rolling down a hill. This isn't wrong, but there is much more to the story.
We often think of optimization with momentum as a ball rolling down a hill. This isn't wrong, but there is much more to the story. -
Science is a human activity. When we fail to distill and explain research, we accumulate a kind of debt...
Science is a human activity. When we fail to distill and explain research, we accumulate a kind of debt... -
Several interactive visualizations of a generative model of handwriting. Some are fun, some are serious.
Several interactive visualizations of a generative model of handwriting. Some are fun, some are serious. -
When we look very closely at images generated by neural networks, we often see a strange checkerboard pattern of artifacts.
When we look very closely at images generated by neural networks, we often see a strange checkerboard pattern of artifacts. - Loading more…