249 citations · 1.2k across the 77 of their papers we have counts for
39 papers · 1 filter
Repurposing Deep Limit Order Book Forecasting for Scenario-Conditioned Market Impact Modeling
Eljas Linna, Kestutis Baltakys, Derrick Manoharan +2
Deep Limit Order Book forecasting models capture nonlinear market dynamics, but their ability to quantify the effects of counterfactual order book messages has not been systematica…
Convolutional autoencoder-based multimodal one-class classification
Firas Laakom, Fahad Sohrab, Jenni Raitoharju +2
One-class classification refers to approaches of learning using data from a single class only. In this paper, we propose a deep learning one-class classification method suitable fo…
On Feature Diversity in Energy-based Models
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis +1
Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches. An energy-based model (EBM) is typically formed of inner-m…
WLD-Reg: A Data-dependent Within-layer Diversity Regularizer
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis +1
Neural networks are composed of multiple layers arranged in a hierarchical structure jointly trained with a gradient-based optimization, where the errors are back-propagated from t…
Generalized Reference Kernel for One-class Classification
Jenni Raitoharju, Alexandros Iosifidis
In this paper, we formulate a new generalized reference kernel hoping to improve the original base kernel using a set of reference vectors. Depending on the selected reference vect…
Constructing Neural Network-Based Models for Simulating Dynamical Systems
Christian Møldrup Legaard, Thomas Schranz, Gerald Schweiger +6
Dynamical systems see widespread use in natural sciences like physics, biology, chemistry, as well as engineering disciplines such as circuit analysis, computational fluid dynamics…
On Quantitative Evaluations of Counterfactuals
Frederik Hvilshøj, Alexandros Iosifidis, Ira Assent
As counterfactual examples become increasingly popular for explaining decisions of deep learning models, it is essential to understand what properties quantitative evaluation metri…
DeepTimeAnomalyViz: A Tool for Visualizing and Post-processing Deep Learning Anomaly Detection Results for Industrial Time-Series
Błażej Leporowski, Casper Hansen, Alexandros Iosifidis
Industrial processes are monitored by a large number of various sensors that produce time-series data. Deep Learning offers a possibility to create anomaly detection methods that c…
Low-Rank Temporal Attention-Augmented Bilinear Network for financial time-series forecasting
Mostafa Shabani, Alexandros Iosifidis
Financial market analysis, especially the prediction of movements of stock prices, is a challenging problem. The nature of financial time-series data, being non-stationary and nonl…
Detecting Faults during Automatic Screwdriving: A Dataset and Use Case of Anomaly Detection for Automatic Screwdriving
Błażej Leporowski, Daniella Tola, Casper Hansen +1
Detecting faults in manufacturing applications can be difficult, especially if each fault model is to be engineered by hand. Data-driven approaches, using Machine Learning (ML) for…
Learning distinct features helps, provably
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis +1
We study the diversity of the features learned by a two-layer neural network trained with the least squares loss. We measure the diversity by the average -distance between the…
ECINN: Efficient Counterfactuals from Invertible Neural Networks
Frederik Hvilshøj, Alexandros Iosifidis, Ira Assent
Counterfactual examples identify how inputs can be altered to change the predicted class of a classifier, thus opening up the black-box nature of, e.g., deep neural networks. We pr…
Graph-Embedded Subspace Support Vector Data Description
Fahad Sohrab, Alexandros Iosifidis, Moncef Gabbouj +1
In this paper, we propose a novel subspace learning framework for one-class classification. The proposed framework presents the problem in the form of graph embedding. It includes…
Visualising Deep Network's Time-Series Representations
Błażej Leporowski, Alexandros Iosifidis
Despite the popularisation of machine learning models, more often than not, they still operate as black boxes with no insight into what is happening inside the model. There exist a…
Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation
Elizabeth Fons, Paula Dawson, Xiao-jun Zeng +2
Data augmentation methods have been shown to be a fundamental technique to improve generalization in tasks such as image, text and audio classification. Recently, automated augment…
AURSAD: Universal Robot Screwdriving Anomaly Detection Dataset
Błażej Leporowski, Daniella Tola, Casper Hansen +1
Screwdriving is one of the most popular industrial processes. As such, it is increasingly common to automate that procedure by using various robots. Even though the automation incr…
Graph Embedding with Data Uncertainty
Firas Laakom, Jenni Raitoharju, Nikolaos Passalis +2
spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. The main aim is to learn a meaningful low dimensional embedding of the data…
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…
Self-Organized Operational Neural Networks with Generative Neurons
Serkan Kiranyaz, Junaid Malik, Habib Ben Abdallah +3
Operational Neural Networks (ONNs) have recently been proposed to address the well-known limitations and drawbacks of conventional Convolutional Neural Networks (CNNs) such as netw…
Saliency-based Weighted Multi-label Linear Discriminant Analysis
Lei Xu, Jenni Raitoharju, Alexandros Iosifidis +1
In this paper, we propose a new variant of Linear Discriminant Analysis (LDA) to solve multi-label classification tasks. The proposed method is based on a probabilistic model for d…
Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol
Lukas Hedegaard, Omar Ali Sheikh-Omar, Alexandros Iosifidis
Domain Adaptation is the process of alleviating distribution gaps between data from different domains. In this paper, we show that Domain Adaptation methods using pair-wise relatio…
Not all domains are equally complex: Adaptive Multi-Domain Learning
Ali Senhaji, Jenni Raitoharju, Moncef Gabbouj +1
Deep learning approaches are highly specialized and require training separate models for different tasks. Multi-domain learning looks at ways to learn a multitude of different task…
Ellipsoidal Subspace Support Vector Data Description
Fahad Sohrab, Jenni Raitoharju, Alexandros Iosifidis +1
In this paper, we propose a novel method for transforming data into a low-dimensional space optimized for one-class classification. The proposed method iteratively transforms data…
Progressive Graph Convolutional Networks for Semi-Supervised Node Classification
Negar Heidari, Alexandros Iosifidis
Graph convolutional networks have been successful in addressing graph-based tasks such as semi-supervised node classification. Existing methods use a network structure defined by t…