Dominik Żurek

• AGH

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 architecture as new tasks are presented. However, many existing solutions do not efficiently exploit model sparsity, and a...

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 architecture as new tasks are presented. However, many existing solutions do not efficiently exploit model sparsity, and a...

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 methods rely on online learning, which requires either real-world hardware or advanced simulation environments--...

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 dataset is a cumbersome and time-consuming process. Neuroevolution could be an effective and efficient solution t...

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 given dataset is a cumbersome and time-consuming process. Neuroevolution could be an effective and efficient soluti...

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 dynamic environments. This goal is realized by designing strategies that simultaneously foster the incorporatio...

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 to expand and adapt the model architecture as new tasks are presented. However, existing solutions do not effic...

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 environments. In this work new architecture based approach Ada-QPacknet is described. It incorporates the pruning for...

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 dataset is a cumbersome and time consuming process. Neuroevolution could be an effective and efficient solution t...

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 dynamic environments. The landscape of CL research is fragmented into several learning evaluation protocols, co...

One of the leading approaches for solving various hard discrete problems is designing advanced solvers based on local search heuristics. This observation is also relevant to the low autocorrelation binary sequence (LABS) – an open hard optimisation problem that has many applications. There are a lot of dedicated heuristics such as the steepest-desc...

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 most effective implementations of deep learning (DL) algorithms for GPUs. GPUs are the most commonly used acceler...

The neuroevolution is one of the methodologies that can be used for learning optimal architecture during the training. It uses evolutionary algorithms to generate topology of artificial neural networks (ANN) and its parameters. In this work, a modified neuroevolution technique is presented which incorporates multi-level optimization. The presented...

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 quite difficult for humans. Algorithms that automate the process of detecting anomalies are crucial in modern...

Multivariate time series anomaly detection is a very common 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 quite difficult for humans. Algorithms which automates the process of detecting anomalies are crucial in mode...

This paper is focused on the improvement of 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 of deep learning (DL) algorithms for GPUs. GPUs are one of the most efficient and commonly used accelerators...

Low autocorrelation binary sequence (LABS) remains an open hard optimisation problem that has many applications. One of the promising directions for solving the problem is designing advanced solvers based on local search heuristics. The paper proposes two new heuristics developed from the steepest-descent local search algorithm (SDLS), implemented...

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 using reduced precision with its original form. The main advantage of using quantization is decrease in computation...

This paper presents an approach to text-based data classification when only a limited number of positive samples are provided with additional challenge that classes are not mutually exclusive. The main goal is to develop an algorithm which can address a specific case of overlapping classes. The proposed solution encompasses a set of steps to be tak...

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 of deep learning (DL) algorithms for GPUs. GPUs are one of the most efficient and commonly used accelerators fo...

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 using reduced precision with its original form. The main advantage of using quantization is decrease in computation...

Agent-based memetic computational systems have been proven to be an efficient concept for solving complex computational problems. In this paper, we propose and evaluate a new hybrid architecture for such systems that effectively utilise CPU and GPGPU processing power by delegating parallel part of computations to GPGPU. The paper illustrates how to...

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 optimal Golomb-ruler (OGR). In the paper as a follow-up of the previous research, a short concept of hybrid agent-bas...

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 the execution performance of the implemented algorithms. We took notice of detection performance, storage requi...

This paper presents preliminary implementation results of the SVM (Support Vector Machine) algorithm. SVM is a dedicated mathematical formula which allows us to extract selective objects from a picture and assign them to an appropriate class. Consequently, a black and white images reflecting an occurrence of the desired feature is derived from an o...

Sorting is a common problem in computer science. There are lot of well-known sorting algorithms created for sequential execution on a single processor. Recently, hardware platforms enable to create wide parallel algorithms. We have standard processors consist of multiple cores and hardware accelerators like GPU. The graphic cards with their paralle...

This paper presents preliminary implementation results of the SVM (Support Vector Machine) algorithm. SVM is a dedicated mathematical formula which allows us to extract selective objects from a picture and assign them to an appropriate class. Consequently, a black and white images reflecting an occurrence of the desired feature is derived from an o...