research

Understanding Convolutions on Graphs

Understanding the building blocks and design choices of graph neural networks.

2 years ago

Distill Hiatus

After five years, Distill will be taking a break.

2 years ago

Weight Banding

Weights in the final layer of common visual models appear as horizontal bands. We investigate how and why.

2 years ago

Adversarial Reprogramming of Neural Cellular Automata

Reprogramming Neural CA to exhibit novel behaviour, using adversarial attacks.

2 years ago

Last call: Stefan Krawcyzk’s ‘Mastering MLOps’ Live Cohort

Tweet Tweet Share Share Last Updated on August 19, 2022 Sponsored Post   This is your last chance to sign…

2 years ago

Why Initialize a Neural Network with Random Weights?

Tweet Tweet Share Share Last Updated on August 15, 2022 The weights of artificial neural networks must be initialized to…

2 years ago

When to Use MLP, CNN, and RNN Neural Networks

Tweet Tweet Share Share Last Updated on August 15, 2022 What neural network is appropriate for your predictive modeling problem?…

2 years ago

Difference Between a Batch and an Epoch in a Neural Network

Tweet Tweet Share Share Last Updated on August 15, 2022 Stochastic gradient descent is a learning algorithm that has a…

2 years ago

Using Depthwise Separable Convolutions in Tensorflow

Tweet Tweet Share Share Last Updated on August 10, 2022 Looking at all of the very large convolutional neural networks…

2 years ago

Reverse engineering the NTK: towards first-principles architecture design

Deep neural networks have enabled technological wonders ranging from voice recognition to machine transition to protein engineering, but their design…

2 years ago