Search Results for author: Konstantinos P. Panousis

Found 12 papers, 4 papers with code

Hierarchical Concept Discovery Models: A Concept Pyramid Scheme

no code implementations3 Oct 2023 Konstantinos P. Panousis, Dino Ienco, Diego Marcos

Deep Learning algorithms have recently gained significant attention due to their impressive performance.

Decision Making

Sparse Linear Concept Discovery Models

1 code implementation21 Aug 2023 Konstantinos P. Panousis, Dino Ienco, Diego Marcos

The recent mass adoption of DNNs, even in safety-critical scenarios, has shifted the focus of the research community towards the creation of inherently intrepretable models.

Macroeconomic forecasting and sovereign risk assessment using deep learning techniques

no code implementations24 Jan 2023 Anastasios Petropoulos, Vassilis Siakoulis, Konstantinos P. Panousis, Loukas Papadoulas, Sotirios Chatzis

In this study, we propose a novel approach of nowcasting and forecasting the macroeconomic status of a country using deep learning techniques.

Econometrics

Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representations

no code implementations10 Jan 2022 Konstantinos P. Panousis, Anastasios Antoniadis, Sotirios Chatzis

To this end, we combine information-theoretic arguments with stochastic competition-based activations, namely Stochastic Local Winner-Takes-All (LWTA) units.

Image Classification Representation Learning

Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness

1 code implementation5 Dec 2021 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-box adversarial attacks; we especially focus on Adversarial Training settings.

Adversarial Attack Adversarial Defense +2

Local Competition and Stochasticity for Adversarial Robustness in Deep Learning

no code implementations4 Jan 2021 Konstantinos P. Panousis, Sotirios Chatzis, Antonios Alexos, Sergios Theodoridis

The main operating principle of the introduced units lies on stochastic arguments, as the network performs posterior sampling over competing units to select the winner.

Adversarial Attack Adversarial Robustness

A Deep Learning Approach for Dynamic Balance Sheet Stress Testing

no code implementations23 Sep 2020 Anastasios Petropoulos, Vassilis Siakoulis, Konstantinos P. Panousis, Loukas Papadoulas, Sotirios Chatzis

Current stress testing methodologies attempt to simulate the risks underlying a financial institution's balance sheet by using several satellite models.

Management

Nonparametric Bayesian Deep Networks with Local Competition

1 code implementation19 May 2018 Konstantinos P. Panousis, Sotirios Chatzis, Sergios Theodoridis

To this end, we revisit deep networks that comprise competing linear units, as opposed to nonlinear units that do not entail any form of (local) competition.

Bayesian Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.