no code implementations • 22 Aug 2020 • Vasilis Margonis, Athanasios Davvetas, Iraklis A. Klampanos
Learning disentangled representations without supervision or inductive biases, often leads to non-interpretable or undesirable representations.
no code implementations • 14 May 2020 • Athanasios Davvetas, Iraklis A. Klampanos
When observing a phenomenon, severe cases or anomalies are often characterised by deviation from the expected data distribution.
no code implementations • 22 Dec 2019 • Athanasios Davvetas, Iraklis A. Klampanos
Evidence transfer is a robust solution against external unknown categorical evidence that can introduce noise or uncertainty.
1 code implementation • 9 Nov 2018 • Athanasios Davvetas, Iraklis A. Klampanos, Vangelis Karkaletsis
In this paper we introduce evidence transfer for clustering, a deep learning method that can incrementally manipulate the latent representations of an autoencoder, according to external categorical evidence, in order to improve a clustering outcome.
1 code implementation • 7 Apr 2018 • Iraklis A. Klampanos, Athanasios Davvetas, Antonis Koukourikos, Vangelis Karkaletsis
Deep learning models, while effective and versatile, are becoming increasingly complex, often including multiple overlapping networks of arbitrary depths, multiple objectives and non-intuitive training methodologies.