4 papers
Relative Position Prediction as Pre-training for Text Encoders
Rickard Brüel-Gabrielsson, Chris Scarvelis
Meaning is defined by the company it keeps. However, company is two-fold: It's based on the identity of tokens and also on their position (topology). We argue that a position-centr…
Universal Function Approximation on Graphs
Rickard Brüel-Gabrielsson
In this work we produce a framework for constructing universal function approximators on graph isomorphism classes. We prove how this framework comes with a collection of theoretic…
A Topology Layer for Machine Learning
Rickard Brüel-Gabrielsson, Bradley J. Nelson, Anjan Dwaraknath +3
Topology applied to real world data using persistent homology has started to find applications within machine learning, including deep learning. We present a differentiable topolog…
Topological Approaches to Deep Learning
Gunnar Carlsson, Rickard Brüel Gabrielsson
We perform topological data analysis on the internal states of convolutional deep neural networks to develop an understanding of the computations that they perform. We apply this u…