Zobrazeno 1 - 10
of 211
pro vyhledávání: '"Chatzis, Sotirios P."'
Despite the prevalence and significance of tabular data across numerous industries and fields, it has been relatively underexplored in the realm of deep learning. Even today, neural networks are often overshadowed by techniques such as gradient boost
Externí odkaz:
http://arxiv.org/abs/2407.13238
Continual learning on edge devices poses unique challenges due to stringent resource constraints. This paper introduces a novel method that leverages stochastic competition principles to promote sparsity, significantly reducing deep network memory fo
Externí odkaz:
http://arxiv.org/abs/2407.10758
Autor:
Voskou, Andreas, Panousis, Konstantinos P., Partaourides, Harris, Tolias, Kyriakos, Chatzis, Sotirios
Publikováno v:
Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023. p. 1966-1975
Automatic Sign Language Translation (SLT) is a research avenue of great societal impact. End-to-End SLT facilitates the interaction of Hard-of-Hearing (HoH) with hearing people, thus improving their social life and opportunities for participation in
Externí odkaz:
http://arxiv.org/abs/2310.04753
Modern deep networks are highly complex and their inferential outcome very hard to interpret. This is a serious obstacle to their transparent deployment in safety-critical or bias-aware applications. This work contributes to post-hoc interpretability
Externí odkaz:
http://arxiv.org/abs/2310.04929
Autor:
Petropoulos, Anastasios, Siakoulis, Vassilis, Panousis, Konstantinos P., Papadoulas, Loukas, Chatzis, Sotirios
In this study, we propose a novel approach of nowcasting and forecasting the macroeconomic status of a country using deep learning techniques. We focus particularly on the US economy but the methodology can be applied also to other economies. Specifi
Externí odkaz:
http://arxiv.org/abs/2301.09856
Publikováno v:
PMLR 162:10586-10597, 2022
This work addresses meta-learning (ML) by considering deep networks with stochastic local winner-takes-all (LWTA) activations. This type of network units results in sparse representations from each model layer, as the units are organized into blocks
Externí odkaz:
http://arxiv.org/abs/2208.01573
Sparse modeling for signal processing and machine learning has been at the focus of scientific research for over two decades. Among others, supervised sparsity-aware learning comprises two major paths paved by: a) discriminative methods and b) genera
Externí odkaz:
http://arxiv.org/abs/2205.14283
This work aims to address the long-established problem of learning diversified representations. To this end, we combine information-theoretic arguments with stochastic competition-based activations, namely Stochastic Local Winner-Takes-All (LWTA) uni
Externí odkaz:
http://arxiv.org/abs/2201.03624
This work explores the potency of stochastic competition-based activations, namely Stochastic Local Winner-Takes-All (LWTA), against powerful (gradient-based) white-box and black-box adversarial attacks; we especially focus on Adversarial Training se
Externí odkaz:
http://arxiv.org/abs/2112.02671
Autor:
Nicolaou, Sergis, Mavrides, Lambros, Tryfou, Georgina, Tolias, Kyriakos, Panousis, Konstantinos, Chatzis, Sotirios, Theodoridis, Sergios
Speech is the most common way humans express their feelings, and sentiment analysis is the use of tools such as natural language processing and computational algorithms to identify the polarity of these feelings. Even though this field has seen treme
Externí odkaz:
http://arxiv.org/abs/2109.07228