Publications (36)
New Gravitational Wave Discoveries Enabled by Machine Learning
Alexandra E. Koloniari, Evdokia C. Koursoumpa, Paraskevi Nousi +4
The detection of gravitational waves has revolutionized our understanding of the universe, offering unprecedented insights into its dynamics. A major goal of gravitational wave dat…
Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks
Nikolaos Passalis, Anastasios Tefas
Convolutional Neural Networks (CNNs) are well established models capable of achieving state-of-the-art classification accuracy for various computer vision tasks. However, they are…
Decoding Generic Visual Representations From Human Brain Activity using Machine Learning
Angeliki Papadimitriou, Nikolaos Passalis, Anastasios Tefas
Among the most impressive recent applications of neural decoding is the visual representation decoding, where the category of an object that a subject either sees or imagines is in…
VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images
Illia Oleksiienko, Paraskevi Nousi, Nikolaos Passalis +2
In this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT). VPIT is the first method that uses voxel pseudo i…
Variational Voxel Pseudo Image Tracking
Illia Oleksiienko, Paraskevi Nousi, Nikolaos Passalis +2
Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving, because it allows creating statistically better perception models and si…
Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data
Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen +2
Time series forecasting is a crucial component of many important applications, ranging from forecasting the stock markets to energy load prediction. The high-dimensionality, veloci…
Interactive dimensionality reduction using similarity projections
Dimitris Spathis, Nikolaos Passalis, Anastasios Tefas
Recent advances in machine learning allow us to analyze and describe the content of high-dimensional data like text, audio, images or other signals. In order to visualize that data…
Multiplicative update rules for accelerating deep learning training and increasing robustness
Manos Kirtas, Nikolaos Passalis, Anastasios Tefas
Even nowadays, where Deep Learning (DL) has achieved state-of-the-art performance in a wide range of research domains, accelerating training and building robust DL models remains a…
Heterogeneous Knowledge Distillation using Information Flow Modeling
Nikolaos Passalis, Maria Tzelepi, Anastasios Tefas
Knowledge Distillation (KD) methods are capable of transferring the knowledge encoded in a large and complex teacher into a smaller and faster student. Early methods were usually l…
Attention-based Neural Bag-of-Features Learning for Sequence Data
Dat Thanh Tran, Nikolaos Passalis, Anastasios Tefas +2
In this paper, we propose 2D-Attention (2DA), a generic attention formulation for sequence data, which acts as a complementary computation block that can detect and focus on releva…
MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
Marlin B. Schäfer, OndÅej Zelenka, Alexander H. Nitz +20
We present the results of the first Machine Learning Gravitational-Wave Search Mock Data Challenge (MLGWSC-1). For this challenge, participating groups had to identify gravitationa…
A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields
Paraskevi Nousi, Emmanouil Mpampis, Nikolaos Passalis +2
In this paper we evaluate the impact of domain shift on human detection models trained on well known object detection datasets when deployed on data outside the distribution of the…
Using Deep Learning for price prediction by exploiting stationary limit order book features
Avraam Tsantekidis, Nikolaos Passalis, Anastasios Tefas +3
The recent surge in Deep Learning (DL) research of the past decade has successfully provided solutions to many difficult problems. The field of quantitative analysis has been slowl…
Quadratic mutual information regularization in real-time deep CNN models
Maria Tzelepi, Anastasios Tefas
In this paper, regularized lightweight deep convolutional neural network models, capable of effectively operating in real-time on devices with restricted computational power for hi…
Deep Learning for Energy Time-Series Analysis and Forecasting
Maria Tzelepi, Charalampos Symeonidis, Paraskevi Nousi +5
Energy time-series analysis describes the process of analyzing past energy observations and possibly external factors so as to predict the future. Different tasks are involved in t…
Using Part-based Representations for Explainable Deep Reinforcement Learning
Manos Kirtas, Konstantinos Tsampazis, Loukia Avramelou +2
Utilizing deep learning models to learn part-based representations holds significant potential for interpretable-by-design approaches, as these models incorporate latent causes obt…
Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillation
Maria Tzelepi, Anastasios Tefas
Knowledge Distillation has been established as a highly promising approach for training compact and faster models by transferring knowledge from heavyweight and powerful models. Ho…
Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling
Styliani-Christina Fragkouli, Paraskevi Nousi, Nikolaos Passalis +3
Deep learning methods have been employed in gravitational-wave astronomy to accelerate the construction of surrogate waveforms for the inspiral of spin-aligned black hole binaries,…
Deep Supervised Hashing leveraging Quadratic Spherical Mutual Information for Content-based Image Retrieval
Nikolaos Passalis, Anastasios Tefas
Several deep supervised hashing techniques have been proposed to allow for efficiently querying large image databases. However, deep supervised image hashing techniques are develop…
Machine Learning for Forecasting Mid Price Movement using Limit Order Book Data
Paraskevi Nousi, Avraam Tsantekidis, Nikolaos Passalis +5
Forecasting the movements of stock prices is one the most challenging problems in financial markets analysis. In this paper, we use Machine Learning (ML) algorithms for the predict…
Bag of Color Features For Color Constancy
Firas Laakom, Nikolaos Passalis, Jenni Raitoharju +4
In this paper, we propose a novel color constancy approach, called Bag of Color Features (BoCF), building upon Bag-of-Features pooling. The proposed method substantially reduces th…
Software Engineering for Self-Adaptive Robotics: A Research Agenda
Hassan Sartaj, Shaukat Ali, Ana Cavalcanti +6
Self-adaptive robotic systems operate autonomously in dynamic and uncertain environments, requiring robust real-time monitoring and adaptive behaviour. Unlike traditional robotic s…
A 262 TOPS Hyperdimensional Photonic AI Accelerator powered by a Si3N4 microcomb laser
Christos Pappas, Antonios Prapas, Theodoros Moschos +13
The ever-increasing volume of data has necessitated a new computing paradigm, embodied through Artificial Intelligence (AI) and Large Language Models (LLMs). Digital electronic AI…
Semantic Scene Segmentation for Robotics Applications
Maria Tzelepi, Anastasios Tefas
Semantic scene segmentation plays a critical role in a wide range of robotics applications, e.g., autonomous navigation. These applications are accompanied by specific computationa…
Dimensionality Reduction using Similarity-induced Embeddings
Nikolaos Passalis, Anastasios Tefas
The vast majority of Dimensionality Reduction (DR) techniques rely on second-order statistics to define their optimization objective. Even though this provides adequate results in…
Roadmap on Neuromorphic Photonics
Daniel Brunner, Bhavin J. Shastri, Mohammed A. Al Qadasi +147
This roadmap consolidates recent advances while exploring emerging applications, reflecting the remarkable diversity of hardware platforms, neuromorphic concepts, and implementatio…
Deep Adaptive Input Normalization for Time Series Forecasting
Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen +2
Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appr…
Learning Deep Representations with Probabilistic Knowledge Transfer
Nikolaos Passalis, Anastasios Tefas
Knowledge Transfer (KT) techniques tackle the problem of transferring the knowledge from a large and complex neural network into a smaller and faster one. However, existing KT meth…
Style Decomposition for Improved Neural Style Transfer
Paraskevas Pegios, Nikolaos Passalis, Anastasios Tefas
Universal Neural Style Transfer (NST) methods are capable of performing style transfer of arbitrary styles in a style-agnostic manner via feature transforms in (almost) real-time.…
Deep Active Perception for Object Detection using Navigation Proposals
Stefanos Ginargiros, Nikolaos Passalis, Anastasios Tefas
Deep Learning (DL) has brought significant advances to robotics vision tasks. However, most existing DL methods have a major shortcoming, they rely on a static inference paradigm i…
Non-negative isomorphic neural networks for photonic neuromorphic accelerators
Manos Kirtas, Nikolaos Passalis, Nikolaos Pleros +1
Neuromorphic photonic accelerators are becoming increasingly popular, since they can significantly improve computation speed and energy efficiency, leading to femtojoule per MAC ef…
Deep Residual Networks for Gravitational Wave Detection
Paraskevi Nousi, Alexandra E. Koloniari, Nikolaos Passalis +3
Traditionally, gravitational waves are detected with techniques such as matched filtering or unmodeled searches based on wavelets. However, in the case of generic black hole binari…
Large Models in Dialogue for Active Perception and Anomaly Detection
Tzoulio Chamiti, Nikolaos Passalis, Anastasios Tefas
Autonomous aerial monitoring is an important task aimed at gathering information from areas that may not be easily accessible by humans. At the same time, this task often requires…
Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling
Paraskevi Nousi, Styliani-Christina Fragkouli, Nikolaos Passalis +5
Recently, artificial neural networks have been gaining momentum in the field of gravitational wave astronomy, for example in surrogate modelling of computationally expensive wavefo…
UAV Active Perception and Motion Control for Improving Navigation Using Low-Cost Sensors
Konstantinos Gounis, Nikolaos Passalis, Anastasios Tefas
In this study a model pipeline is proposed that combines computer vision with control-theoretic methods and utilizes low cost sensors. The proposed work enables perception-aware mo…
Leveraging Deep Learning and Online Source Sentiment for Financial Portfolio Management
Paraskevi Nousi, Loukia Avramelou, Georgios Rodinos +10
Financial portfolio management describes the task of distributing funds and conducting trading operations on a set of financial assets, such as stocks, index funds, foreign exchang…