Automated testing in machine learning
Subequivariant Meshgraphnets⭐
An experiment trying to extend Learning Mesh-Based Simulation with Graph Networks which remains competitive in mesh based simulation by making the model subequivariant.
Running models on edge devices is a win-win for users and providers
Quantization is unreasonably effective
You Shouldn't Use Grid Search
Thinking about Neural Network Layers
Is this a tank? - The Pentagon
SHArP-ray: Interpretability of Chest X-rays: Aarhus Critical Datathon 2019
During a Datathon, we found evidence of misfitting in medical baseline models picking up text added to x-ray scan for classifying pathologies instead of the actual pathology location.
Introduction To The Basics Of Neural Networks
In recent years, neural networks have shown great potential across a wide range of industries. In this series, we look at how neural networks work from a theoretical point of view.
How to intuitively understand neural networks
Gradient Descent: How Machines Learn
How Does Backpropagation Work?
Computational Complexity Of Neural Networks
What Is A Neural Network?
Just How Fast Is Your Algorithm?
Creating Your First Machine Learning Classifier with Sklearn
