Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Margeloiu, Andrei"'
Data collection is often difficult in critical fields such as medicine, physics, and chemistry. As a result, classification methods usually perform poorly with these small datasets, leading to weak predictive performance. Increasing the training set
Externí odkaz:
http://arxiv.org/abs/2409.16118
Tabular data is prevalent in many critical domains, yet it is often challenging to acquire in large quantities. This scarcity usually results in poor performance of machine learning models on such data. Data augmentation, a common strategy for perfor
Externí odkaz:
http://arxiv.org/abs/2406.01805
Variational Autoencoders and their many variants have displayed impressive ability to perform dimensionality reduction, often achieving state-of-the-art performance. Many current methods however, struggle to learn good representations in High Dimensi
Externí odkaz:
http://arxiv.org/abs/2306.15661
Tabular biomedical data poses challenges in machine learning because it is often high-dimensional and typically low-sample-size (HDLSS). Previous research has attempted to address these challenges via local feature selection, but existing approaches
Externí odkaz:
http://arxiv.org/abs/2306.12330
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 more sophisticated architectures on tabular data, they are still pron
Externí odkaz:
http://arxiv.org/abs/2211.15616
Neural networks often struggle with high-dimensional but small sample-size tabular datasets. One reason is that current weight initialisation methods assume independence between weights, which can be problematic when there are insufficient samples to
Externí odkaz:
http://arxiv.org/abs/2211.06302
Autor:
Margeloiu, Andrei, Ashman, Matthew, Bhatt, Umang, Chen, Yanzhi, Jamnik, Mateja, Weller, Adrian
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 procedure, and have been motivated to meet three desiderata: interpretab
Externí odkaz:
http://arxiv.org/abs/2105.04289
We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer. We show that gradient-based saliency maps of adversarially trained CNNs are signific
Externí odkaz:
http://arxiv.org/abs/2012.01166
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 more sophisticated architectures on tabular data, they are still pron
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a40481f1fc886c83f2fca5ca4b075fe
Tabular biomedical data poses challenges in machine learning because it is often high-dimensional and typically low-sample-size. Previous research has attempted to address these challenges via feature selection approaches, which can lead to unstable
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f5caaf427d8d4a68c5d2a9667bbd600