Dominik Żurek
YOU?
Author Swipe
View article: xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection
xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection Open
The recently proposed xLSTM is a powerful model that leverages expressive multiplicative gating and residual connections, providing the temporal capacity needed for long-horizon forecasting and representation learning. This architecture ha…
View article: Innovative artificial intelligence for practice management in medical healthcare
Innovative artificial intelligence for practice management in medical healthcare Open
View article: TinySubNets: An Efficient and Low Capacity Continual Learning Strategy
TinySubNets: An Efficient and Low Capacity Continual Learning Strategy Open
Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effective due to their potential to adapt the model architectur…
View article: TinySubNets: An efficient and low capacity continual learning strategy
TinySubNets: An efficient and low capacity continual learning strategy Open
Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effective due to their potential to adapt the model architectur…
View article: Solving Multi-Goal Robotic Tasks with Decision Transformer
Solving Multi-Goal Robotic Tasks with Decision Transformer Open
Artificial intelligence plays a crucial role in robotics, with reinforcement learning (RL) emerging as one of the most promising approaches for robot control. However, several key challenges hinder its broader application. First, many RL m…
View article: AD-NEv: A Scalable Multilevel Neuroevolution Framework for Multivariate Anomaly Detection
AD-NEv: A Scalable Multilevel Neuroevolution Framework for Multivariate Anomaly Detection Open
Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given da…
View article: From MNIST to ImageNet and back: benchmarking continual curriculum learning
From MNIST to ImageNet and back: benchmarking continual curriculum learning Open
Continual learning (CL) is one of the most promising trends in recent machine learning research. Its goal is to go beyond classical assumptions in machine learning and develop models and learning strategies that present high robustness in …
View article: AD-NEv++ : The multi-architecture neuroevolution-based multivariate anomaly detection framework
AD-NEv++ : The multi-architecture neuroevolution-based multivariate anomaly detection framework Open
Anomaly detection tools and methods enable key analytical capabilities in modern cyberphysical and sensor-based systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a give…
View article: Towards efficient deep autoencoders for multivariate time series anomaly detection
Towards efficient deep autoencoders for multivariate time series anomaly detection Open
Multivariate time series anomaly detection is a crucial problem in many industrial and research applications. Timely detection of anomalies allows, for instance, to prevent defects in manufacturing processes and failures in cyberphysical s…
View article: Ada-QPacknet – Multi-Task Forget-Free Continual Learning with Quantization Driven Adaptive Pruning
Ada-QPacknet – Multi-Task Forget-Free Continual Learning with Quantization Driven Adaptive Pruning Open
Continual learning (CL) is a challenging machine learning setting that is attracting the interest of an increasing number of researchers. Among recent CL works, architectural strategies appear particularly promising due to their potential …
View article: Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting
Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting Open
Continual Learning (CL) is a process in which there is still huge gap between human and deep learning model efficiency. Recently, many CL algorithms were designed. Most of them have many problems with learning in dynamic and complex enviro…
View article: AD-NEV: A Scalable Multi-level Neuroevolution Framework for Multivariate Anomaly Detection
AD-NEV: A Scalable Multi-level Neuroevolution Framework for Multivariate Anomaly Detection Open
Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given da…
View article: From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learning
From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learning Open
Continual learning (CL) is one of the most promising trends in recent machine learning research. Its goal is to go beyond classical assumptions in machine learning and develop models and learning strategies that present high robustness in …
View article: Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction
Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction Open
This work is focused on the pruning of some convolutional neural networks (CNNs) and improving theirs efficiency on graphic processing units (GPU) by using a direct sparse algorithm. The Nvidia deep neural network (cuDnn) library is the mo…
View article: Fast and scalable neuroevolution deep learning architecture search for multivariate anomaly detection
Fast and scalable neuroevolution deep learning architecture search for multivariate anomaly detection Open
Neuroevolution is one of the methodologies that can be used for learning optimal architecture during training. It uses evolutionary algorithms to generate the topology of artificial neural networks and its parameters. The main benefits are…
View article: Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection
Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection Open
Multivariate time series anomaly detection is a widespread problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors in novel industry systems makes the anomaly detection process…
View article: Ensemble neuroevolution based approach for multivariate time series\n anomaly detection
Ensemble neuroevolution based approach for multivariate time series\n anomaly detection Open
Multivariate time series anomaly detection is a very common problem in the\nfield of failure prevention. Fast prevention means lower repair costs and\nlosses. The amount of sensors in novel industry systems makes the anomaly\ndetection pro…
View article: When deep learning models on GPU can be accelerated by taking advantage of unstructured sparsity
When deep learning models on GPU can be accelerated by taking advantage of unstructured sparsity Open
This paper is focused on the improvement the efficiency of the sparse convolutional neural networks (CNNs) layers on graphic processing units (GPU). The Nvidia deep neural network (cuDnn) library provides the most effective implementation …
View article: When deep learning models on GPU can be accelerated by taking advantage\n of unstructured sparsity
When deep learning models on GPU can be accelerated by taking advantage\n of unstructured sparsity Open
This paper is focused on the improvement the efficiency of the sparse\nconvolutional neural networks (CNNs) layers on graphic processing units (GPU).\nThe Nvidia deep neural network (cuDnn) library provides the most effective\nimplementati…
View article: Training with reduced precision of a support vector machine model for text classification
Training with reduced precision of a support vector machine model for text classification Open
This paper presents the impact of using quantization on the efficiency of multi-class text classification in the training process of a support vector machine (SVM). This work is focused on comparing the efficiency of SVM model trained usin…
View article: Evaluation and Implementation of n-Gram-Based Algorithm for Fast Text Comparison
Evaluation and Implementation of n-Gram-Based Algorithm for Fast Text Comparison Open
This paper presents a study of an n-gram-based document comparison method. The method is intended to build a large-scale plagiarism detection system. The work focuses not only on an efficiency of the text similarity extraction but also on …
View article: Toward hybrid platform for evolutionary computations of hard discrete problems
Toward hybrid platform for evolutionary computations of hard discrete problems Open
Memetic agent-based paradigm, which combines evolutionary computation and local search techniques in one of promising meta-heuristics for solving large and hard discrete problem such as Low Autocorrellation Binary Sequence (LABS) or optima…
View article: Liveness detection in remote biometrics based on gaze direction estimation
Liveness detection in remote biometrics based on gaze direction estimation Open
The following paper presents a simple and fast liveness detection method based on gaze direction estimation under a challenge-response user authentication scenario.To estimate a line of sight, a procedure composed of several steps, includi…
View article: Supervised Kernel Principal Component Analysis by Most Expressive Feature Reordering
Supervised Kernel Principal Component Analysis by Most Expressive Feature Reordering Open
The presented paper is concerned with feature space derivation through feature selection. The selection is performed on results of kernel Principal Component Analysis (kPCA) of input data samples. Several criteria that drive feature select…