116 citations · 137 across the 24 of their papers we have counts for
17 papers · 1 filter
Lévy Attention: Single-Pass Predictive Uncertainty for Continuous-Time Attention
Sotirios P. Chatzis, Loukas Papadoulas
Deep models for irregularly-sampled time series answer queries at arbitrary continuous timestamps, yet report nothing about how far each answer should be trusted. We show the atten…
Transformers with Stochastic Competition for Tabular Data Modelling
Andreas Voskou, Charalambos Christoforou, Sotirios Chatzis
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, neura…
Continual Deep Learning on the Edge via Stochastic Local Competition among Subnetworks
Theodoros Christophides, Kyriakos Tolias, Sotirios Chatzis
Continual learning on edge devices poses unique challenges due to stringent resource constraints. This paper introduces a novel method that leverages stochastic competition princip…
Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning
Konstantinos Kalais, Sotirios Chatzis
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 represen…
Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representations
Konstantinos P. Panousis, Anastasios Antoniadis, Sotirios Chatzis
This work aims to address the long-established problem of learning diversified representations. To this end, we combine information-theoretic arguments with stochastic competition-…
Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness
Konstantinos P. Panousis, Sotirios Chatzis, Sergios Theodoridis
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-b…
Local Competition and Stochasticity for Adversarial Robustness in Deep Learning
Konstantinos P. Panousis, Sotirios Chatzis, Antonios Alexos +1
This work addresses adversarial robustness in deep learning by considering deep networks with stochastic local winner-takes-all (LWTA) activations. This type of network units resul…
Local Competition and Uncertainty for Adversarial Robustness in Deep Learning
Antonios Alexos, Konstantinos P. Panousis, Sotirios Chatzis
This work attempts to address adversarial robustness of deep networks by means of novel learning arguments. Specifically, inspired from results in neuroscience, we propose a local…
Variational Conditional Dependence Hidden Markov Models for Skeleton-Based Action Recognition
Konstantinos P. Panousis, Sotirios Chatzis, Sergios Theodoridis
Hidden Markov Models (HMMs) comprise a powerful generative approach for modeling sequential data and time-series in general. However, the commonly employed assumption of the depend…
t-Exponential Memory Networks for Question-Answering Machines
Kyriakos Tolias, Sotirios Chatzis
Recent advances in deep learning have brought to the fore models that can make multiple computational steps in the service of completing a task; these are capable of describ- ing l…
Amortized Context Vector Inference for Sequence-to-Sequence Networks
Kyriacos Tolias, Ioannis Kourouklides, Sotirios Chatzis
Neural attention (NA) has become a key component of sequence-to-sequence models that yield state-of-the-art performance in as hard tasks as abstractive document summarization (ADS)…
Nonparametric Bayesian Deep Networks with Local Competition
Konstantinos P. Panousis, Sotirios Chatzis, Sergios Theodoridis
The aim of this work is to enable inference of deep networks that retain high accuracy for the least possible model complexity, with the latter deduced from the data during inferen…
Deep Network Regularization via Bayesian Inference of Synaptic Connectivity
Harris Partaourides, Sotirios P. Chatzis
Deep neural networks (DNNs) often require good regularizers to generalize well. Currently, state-of-the-art DNN regularization techniques consist in randomly dropping units and/or…
Deep learning with t-exponential Bayesian kitchen sinks
Harris Partaourides, Sotirios Chatzis
Bayesian learning has been recently considered as an effective means of accounting for uncertainty in trained deep network parameters. This is of crucial importance when dealing wi…
Indian Buffet Process Deep Generative Models for Semi-Supervised Classification
Sotirios P. Chatzis
Deep generative models (DGMs) have brought about a major breakthrough, as well as renewed interest, in generative latent variable models. However, DGMs do not allow for performing…
Mixture Gaussian Process Conditional Heteroscedasticity
Emmanouil A. Platanios, Sotirios P. Chatzis
Generalized autoregressive conditional heteroscedasticity (GARCH) models have long been considered as one of the most successful families of approaches for volatility modeling in f…
The Kernel Pitman-Yor Process
Sotirios P. Chatzis, Dimitrios Korkinof, Yiannis Demiris
In this work, we propose the kernel Pitman-Yor process (KPYP) for nonparametric clustering of data with general spatial or temporal interdependencies. The KPYP is constructed by fi…