The effect of variable labels on deep learning models trained to predict breast density

no code implementations • 8 Oct 2022 • Steven Squires, Elaine F. Harkness, D. Gareth Evans, Susan M. Astley

However, when we train different models to investigate the representation effect we see little difference, with Spearman rank correlation coefficients of $0. 846\pm0. 006$ and $0. 850\pm0. 006$ showing no statistically significant difference in the quality of the model representation with regard to density prediction.

Transfer Learning

A Variational Autoencoder for Probabilistic Non-Negative Matrix Factorisation

no code implementations • ICLR 2019 • Steven Squires, Adam Prügel Bennett, Mahesan Niranjan

We design a network which can perform non-negative matrix factorisation (NMF) and add in aspects of a VAE to make the coefficients of the latent space probabilistic.

Time Series Time Series Analysis

Minimum description length as an objective function for non-negative matrix factorization

no code implementations • 5 Feb 2019 • Steven Squires, Adam Prugel Bennett, Mahesan Niranjan

Non-negative matrix factorization (NMF) is a dimensionality reduction technique which tends to produce a sparse representation of data.

Dimensionality Reduction