Maciej Wielgosz
AGH University of Science and Technology
Deep learningComputer engineeringAlgorithmMachine learningSupport vector machineData miningRecurrent neural networkHierarchical temporal memoryArtificial intelligenceSuperconducting magnetParallel computingSet (abstract data type)Pattern recognitionQuantization (signal processing)Computer scienceField-programmable gate arrayArtificial neural networkSpeedupAnomaly detectionReal-time computingConvolutional neural networkLarge Hadron ColliderComputer hardwareImage processing
69Publications
9H-index
289Citations
Publications 68
Newest
Source
#1Marcin Pietron (AGH University of Science and Technology)H-Index: 6
#2Maciej Wielgosz (AGH University of Science and Technology)H-Index: 9
Convolutional neural networks (CNN) play a major role in image processing tasks like image classification, object detection, semantic segmentation. Very often CNN networks have from several to hundred stacked layers with several megabytes of weights. One of the possible methods to reduce complexity and memory footprint is pruning. Pruning is a process of removing weights which connect neurons from two adjacent layers in the network. The process of finding near optimal solution with specified dro...
#1Mo’taz Al-Hami (HU: Hashemite University)H-Index: 2
#2Marcin PietronH-Index: 6
Last. Maciej WielgoszH-Index: 9
view all 4 authors...
Deep learning has made a real revolution in the embedded computing environment. Convolutional neural network (CNN) revealed itself as a reliable fit to many emerging problems. The next step, is to enhance the CNN role in the embedded devices including both implementation details and performance. Resources needs of storage and computational ability are limited and constrained, resulting in key issues we have to consider in embedded devices. Compressing (i.e., quantizing) the CNN network is a valu...
12 CitationsSource
#1Marcin Pietron (AGH University of Science and Technology)H-Index: 6
#2Michal Karwatowski (AGH University of Science and Technology)H-Index: 5
Last. Jerzy Duda (AGH University of Science and Technology)H-Index: 7
view all 4 authors...
Nowadays, recurrent neural networks (RNN) and convolutional neural networks (CNN) play a major role in a lot of natural language domains like text document categorization, part of speech tagging, chatbots, language modeling or language translation. Very often RNN networks have a few stacked layers with several megabytes of memory, the same is in case of CNN networks. In many domains like automatic speech recognition the real time inference is a crucial factor to achieve satisfactory quality of s...
4 CitationsSource
#1Maciej Wielgosz (AGH University of Science and Technology)H-Index: 9
#2Andrzej Skoczeń (AGH University of Science and Technology)H-Index: 8
Source
#2Maciej WielgoszH-Index: 9
Last. Matej MertikH-Index: 5
view all 3 authors...
Falls prevention, especially in older people, becomes an increasingly important topic in the times of aging societies. In this work, we present Gated Recurrent Unit-based neural networks models designed for predicting falls (syncope). The cardiovascular systems signals used in the study come from Gravitational Physiology, Aging and Medicine Research Unit, Institute of Physiology, Medical University of Graz. We used two of the collected signals, heart rate, and mean blood pressure. By using bidir...
#1Maciej Wielgosz (AGH University of Science and Technology)H-Index: 9
#2Michal Karwatowski (AGH University of Science and Technology)H-Index: 5
Internet of things (IoT) infrastructure, fast access to knowledge becomes critical. In some application domains, such as robotics, autonomous driving, predictive maintenance, and anomaly detection, the response time of the system is more critical to ensure Quality of Service than the quality of the answer. In this paper, we propose a methodology, a set of predefined steps to be taken in order to map the models to hardware, especially field programmable gate arrays (FPGAs), with the main focus on...
8 CitationsSource
#1Michal MarkiewiczH-Index: 9
#2Maciej WielgoszH-Index: 9
Last. Liliana KowalczykH-Index: 2
view all 6 authors...
2 CitationsSource
#1Maciej WielgoszH-Index: 9
#2Andrzej SkoczeńH-Index: 8
Last. Ernesto De MatteisH-Index: 5
view all 3 authors...
: Sensing the voltage developed over a superconducting object is very important in order to make superconducting installation safe. An increase in the resistive part of this voltage (quench) can lead to significant deterioration or even to the destruction of the superconducting device. Therefore, detection of anomalies in time series of this voltage is mandatory for reliable operation of superconducting machines. The largest superconducting installation in the world is the main subsystem of the ...
7 CitationsSource
#1Maciej Wielgosz (AGH University of Science and Technology)H-Index: 9
#2Matej Mertik (Alma Mater Europaea)H-Index: 5
Last. Ernesto De Matteis (CERN)H-Index: 5
view all 4 authors...
Abstract This paper focuses on an examination of an applicability of Recurrent Neural Network models for detecting anomalous behavior of the CERN superconducting magnets. In order to conduct the experiments, the authors designed and implemented an adaptive signal quantization algorithm and a custom Gated Recurrent Unit-based detector and developed a method for the detector parameters selection. Three different datasets were used for testing the detector. Two artificially generated datasets were ...
8 CitationsSource