5 citations · 5 across the 3 of their papers we have counts for
5 papers · 1 filter
Enhancing Representation Learning on High-Dimensional, Small-Size Tabular Data: A Divide and Conquer Method with Ensembled VAEs
Navindu Leelarathna, Andrei Margeloiu, Mateja Jamnik +1
Variational Autoencoders and their many variants have displayed impressive ability to perform dimensionality reduction, often achieving state-of-the-art performance. Many current m…
Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data
Andrei Margeloiu, Nikola Simidjievski, Pietro Lio +1
Tabular biomedical data is often high-dimensional but with a very small number of samples. Although recent work showed that well-regularised simple neural networks could outperform…
GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data
Andrei Margeloiu, Nikola Simidjievski, Pietro Lio +1
Neural networks often struggle with high-dimensional but small sample-size tabular datasets. One reason is that current weight initialisation methods assume independence between we…
Do Concept Bottleneck Models Learn as Intended?
Andrei Margeloiu, Matthew Ashman, Umang Bhatt +3
Concept bottleneck models map from raw inputs to concepts, and then from concepts to targets. Such models aim to incorporate pre-specified, high-level concepts into the learning pr…
Improving Interpretability in Medical Imaging Diagnosis using Adversarial Training
Andrei Margeloiu, Nikola Simidjievski, Mateja Jamnik +1
We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer. We show that g…