Filtry
wszystkich: 1627
-
Katalog
- Publikacje 1064 wyników po odfiltrowaniu
- Czasopisma 120 wyników po odfiltrowaniu
- Konferencje 98 wyników po odfiltrowaniu
- Osoby 82 wyników po odfiltrowaniu
- Projekty 6 wyników po odfiltrowaniu
- Kursy Online 152 wyników po odfiltrowaniu
- Wydarzenia 5 wyników po odfiltrowaniu
- Dane Badawcze 100 wyników po odfiltrowaniu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: ARTIFICIAL INTELLIGENCE TRAINING
-
Towards Scalable Simulation of Federated Learning
PublikacjaFederated learning (FL) allows to train models on decentralized data while maintaining data privacy, which unlocks the availability of large and diverse datasets for many practical applications. The ongoing development of aggregation algorithms, distribution architectures and software implementations aims for enabling federated setups employing thousands of distributed devices, selected from millions. Since the availability of...
-
Bees Detection on Images: Study of Different Color Models for Neural Networks
PublikacjaThis paper presents an approach to bee detection in video streams using a neural network classifier. We describe the motivation for our research and the methodology of data acquisition. The main contribution to this work is a comparison of different color models used as an input format for a feedforward convolutional architecture applied to bee detection. The detection process has is based on a neural binary classifier that classifies...
-
Poprawa jakości klasyfikacji głębokich sieci neuronowych poprzez optymalizację ich struktury i dwuetapowy proces uczenia
PublikacjaW pracy doktorskiej podjęto problem realizacji algorytmów głębokiego uczenia w warunkach deficytu danych uczących. Głównym celem było opracowanie podejścia optymalizującego strukturę sieci neuronowej oraz zastosowanie uczeniu dwuetapowym, w celu uzyskania mniejszych struktur, zachowując przy tym dokładności. Proponowane rozwiązania poddano testom na zadaniu klasyfikacji znamion skórnych na znamiona złośliwe i łagodne. W pierwszym...
-
Paweł Rościszewski dr inż.
OsobyPaweł Rościszewski received his PhD in Computer Science at Gdańsk University of Technology in 2018 based on PhD thesis entitled: "Optimization of hybrid parallel application execution in heterogeneous high performance computing systems considering execution time and power consumption". Currently, he is an Assistant Professor at the Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Poland....
-
Leszek Ziemczonek dr
OsobyUniversity education 1973-1978 – Nicolaus Copernicus University in Toruń, University of Gdańsk in Gdańsk, Mathematical Physics, M. Sc. 1979 – Diploma of Postgraduate Studies, Pedagogics 1989 – Institute of Physics, Polish Academy of Sciences in Warsaw, Theoretical Physics, Ph. D. 2010-2012 – Diploma of Postgraduate Studies, Mathematics Training: · 09.1983 – Trieste (Italy) – International Centre for Theoretical Physics...
-
Train the trainer course
PublikacjaThis chapter presents the concept, evaluation and evaluation results for the train the trainer. This concept of train the trainers is prepared within Workpackage 5 of EU-funded project: MASTER BSR (Erasmus+ Strategic Partnership Programme). Due to the nature of adult learning the content is designed for the use of participatory methods (involved, active). This method uses various techniques of active learning e.g. group work,...
-
Marek Biziuk prof. dr hab. inż.
OsobyUr. 25.06.1947 w Sokółce, Województwo Podlaskie. W latach 1964-1969 studiował na Wydziale Chemicznym PG. Stopień doktora nauk technicznych uzyskał w 1977 r., a stopień doktora habilitowanego nauk chemicznych w zakresie chemia uzyskał na Wydziale Chemicznym PG 24.05.1995 r. Tytuł naukowy profesora nauk chemicznych uzyskał na Wydz. Chemicznym PG 6.04.2001 r. Członek Komitetu Chemii Analitycznej PAN od 2008, członek Zespołu ds....
-
An odor-sensing system - powerful technique for foodstuff studies
PublikacjaThis work examines gas sensor array technology combined with multivariate data processing methods and demonstrates a promising potential for rapid, non-destructive analysis of food. Main attention is focused on detailed description of sensor used in e-nose instruments, construction, and principle of operation of these systems. Moreover, this paper briefly reviews the progress in the field of artificial olfaction and future trends...
-
Development and test of fex, a fingers extending exoskeleton for rehabilitation and regaining mobility
PublikacjaThis paper presents the design process of an exoskeleton for executing human fingers' extension movement for the rehabilitation procedures and as an active orthosis purposes, together with its first clinical usability tests of a robotic exoskeleton. Furthermore, the Fingers Extending eXoskeleton (FEX) is a serial, under-actuated mechanism capable of executing fingers' extension. FEX is based on the state-of-art FingerSpine serial...
-
Creating new voices using normalizing flows
PublikacjaCreating realistic and natural-sounding synthetic speech remains a big challenge for voice identities unseen during training. As there is growing interest in synthesizing voices of new speakers, here we investigate the ability of normalizing flows in text-to-speech (TTS) and voice conversion (VC) modes to extrapolate from speakers observed during training to create unseen speaker identities. Firstly, we create an approach for TTS...
-
Narzędzia treningu twórczości jako pomoc w kształceniu projektantów
PublikacjaKreatywność rozwijać. Na tym założeniu opiera się międzynarodowy program edukacyjny Odyssey of the Mind (Odyseja Umysłu). W programie zespoły młodych osób pracują metodą projektową, wykorzystując różnorodne techniki treningu twórczości, nad rozwiązaniem abstrakcyjnego problemu rozbieżnego. Część absolwentów programu wybiera kierunki kreatywne jako naturalną kontynuację procesu edukacji. Elementy treningu twórczości można wykorzystać...
-
The Double Cognitive Bias of Mistakes: A Measurement Method
PublikacjaThere is no learning without mistakes. However, making mistakes among knowledge workers is s�ll seeing shameful. There is a clash between posi�ve a�tudes and beliefs regarding the power of gaining new (tacit) knowledge by ac�ng in new contexts and nega�ve a�tudes and beliefs toward accompanying mistakes that are sources of learning. These contradictory a�tudes create a bias that is doubled by the other shared solid belief...
-
IEEE Swarm Intelligence Symposium
Konferencje -
Engineering Applications of Artifical Intelligence
Konferencje -
European Conference on Ambient Intelligence
Konferencje -
Immersive Technologies that Aid Additive Manufacturing Processes in CBRN Defence Industry
PublikacjaTesting unique devices or their counterparts for CBRN (C-chemical, B-biological, R-radiological, N-nuclear) defense relies on additive manufacturing processes. Immersive technologies aid additive manufacturing. Their use not only helps understand the manufacturing processes, but also improves the design and quality of the products. This article aims to propose an approach to testing CBRN reconnaissance hand-held products developed...
-
Document Agents with the Intelligent Negotiations Capability
PublikacjaThe paper focus is on augmenting proactive document-agents with built -in intelligence to enable them to recognize execution context provided by devices visited durning the business process, and to reach collaboration agreement despite of their conflicting requirements. We propose a solution based on neural networks to improve simple multi-issue negotiation between the document and the device, practically with no excessive cost...
-
Towards bees detection on images: study of different color models for neural networks
PublikacjaThis paper presents an approach to bee detection in videostreams using a neural network classifier. We describe the motivationfor our research and the methodology of data acquisition. The maincontribution to this work is a comparison of different color models usedas an input format for a feedforward convolutional architecture appliedto bee detection. The detection process has is based on a neural...
-
Automated detection of pronunciation errors in non-native English speech employing deep learning
PublikacjaDespite significant advances in recent years, the existing Computer-Assisted Pronunciation Training (CAPT) methods detect pronunciation errors with a relatively low accuracy (precision of 60% at 40%-80% recall). This Ph.D. work proposes novel deep learning methods for detecting pronunciation errors in non-native (L2) English speech, outperforming the state-of-the-art method in AUC metric (Area under the Curve) by 41%, i.e., from...
-
Conference on Artificial Neural Networks and Expert systems
Konferencje -
Computer-assisted assessment of learning outcomes in the laboratory of metrology
PublikacjaIn the paper, didactic experience with broad and rapid continuous assessment of students’ knowledge, skills and competencies in the Laboratory of Metrology, which is an example of utilisation of assessment for learning, is presented. A learning management system was designed for manage, tracking, reporting of learning program and assessing learning outcomes. It has ability to provide with immediate feedback, which is used by the...
-
PROJEKTOWANIE STANOWISK LABORATORYJNYCH WSPIERAJĄCYCH PROCES SZKOLENIA PRAKTYCZNEGO KADR MORSKICH DZIAŁU MASZYNOWEGO W ŻEGLUDZE MIĘDZYNARODOWEJ, PRZYBRZEŻNEJ I KRAJOWEJ
PublikacjaWithin the article a design offer of the Department of Ship and Power Plants of the Faculty of Ocean Engineering And Ship Technology at the Gdansk University of Technology has been presented. The offer concerns designing laboratory stations which might stand for the equipment of a didactic base of maritime educational centers i.e. maritime (naval) academies and schools as well as maritime affairs' professional training centers,...
-
Zastosowanie metody studium przypadku w kształceniu menedżerów
PublikacjaKształcenie z wykorzystaniem metod rozwiązywania problemów (problem-based learning) staje się coraz bardziej popularne na wszystkich poziomach kształcenia, również w edukacji biznesowej. Przykładem takiej metody jest studium przypadku (case study). Metoda studium przypadku pozwala na rozwijanie umiejętności i kompetencji wykorzystywanych przez menedżerów w ich pracy, np. umiejętności syntezy, identyfikacji problemów, czy podejmowania...
-
Strategie treningu neuronowego estymatora częstotliwości tonu krtaniowego z użyciem generatora syntetycznych samogłosek
PublikacjaW wielu zastosowaniach telekomunikacyjnych pojawia się problem przetwarzania lub analizy sygnału mowy, w ramach którego, często w obszarze podstawowych algorytmów, stosuje się estymator częstotliwości tonu krtaniowego. Estymator rozpatrywany w tej pracy bazuje na neuronowym klasyfikatorze podejmującym decyzje na podstawie częstotliwości oraz mocy chwilowej wyznaczanych w podpasmach analizowanego sygnału mowy. W pracy rozważamy...
-
BASICS OF THE MANAGEMENT SYSTEM FOR TRANSFORMATIONS OF PRODUCTION PLANNING AND CONTROL PROCESSES
PublikacjaIntensive development of technologies, in particular of the spinotronics, nanotechnology, robotics, and ICT, shapes the new generation production systems. Their distinctive feature is the flexi-bility associated with production intelligence. It is required from all processes, including the production planning and control processes (PPCP). The article is of conceptual character. It was prepared based on literature research. It encompasses...
-
Justyna Signerska-Rynkowska dr inż.
OsobySince 2021 visiting assistant professor in Dioscuri Centre in Topological Data Analysis (Institute of Mathematics of the Polish Academy of Sciences, IMPAN) Since 2016 assistant professor at Gdańsk University of Technology, Faculty of Applied Physics and Mathematics, Department of Differential Equations and Mathematics Applications 2020 - 2023 Principal Investigator in "SONATA" grant “Challenges of low-dimensional...
-
Double Bias of Mistakes: Essence, Consequences, and Measurement Method
PublikacjaThere is no learning without mistakes. However, there is a clash between‘positive attitudes and beliefs’regarding learning processes and the ‘negative attitudes and beliefs’towardthese being accompanied bymistakes. Thisclash exposesa cognitive bias towardmistakesthat might block personal and organizational learning. This study presents an advanced measurement method to assess thebias of mistakes. The essence of it is the...
-
Assessment of Therapeutic Progress After Acquired Brain Injury Employing Electroencephalography and Autoencoder Neural Networks
PublikacjaA method developed for parametrization of EEG signals gathered from participants with acquired brain injuries is shown. Signals were recorded during therapeutic session consisting of a series of computer assisted exercises. Data acquisition was performed in a neurorehabilitation center located in Poland. The presented method may be used for comparing the performance of subjects with acquired brain injuries (ABI) who are involved...
-
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
PublikacjaThis paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically de...
-
Fuzzy Methods and Models for a Team-Building Process
PublikacjaThis chapter contains an introduction to fuzzy-logic model-based approaches for a team-building process. Such appraches allow extending typical recruiting practice and selection processes to enable a wider and more precise assessment of a new team and/or existing team members, taking into account both their hard and soft skills. Moreover, as effectiveness of teams depends on the interpersonal skills and emotional intelligence...
-
Neural network simulator's application to reference performance determination of turbine blading in the heat-flow diagnostics.
PublikacjaIn the paper, the possibility of application of artificial neural networks to perform the fluid flow calculations through both damaged and undamaged turbine blading was investigated. Preliminary results are presented and show the potentiality of further development of the method for the purpose of heat-flow diagnostics.
-
Modeling of Ice Phenomena in the Mouth of the Vistula River
PublikacjaThe mouth of the Vistula River, which is a river outlet located in tideless area, is analyzed. The Vistula River mouth is a man-made, artificial channel which was built in the 19th century in order to prevent the formation of ice jams in the natural river delta. Since the artificial river outlet was constructed, no severe ice-related flood risk situations have ever occurred. However, periodic ice-related phenomena still have an impact...
-
A system for acoustic field measurement employing cartesian robot
PublikacjaA system setup for measurements of acoustic field, together with the results of 3D visualisations of acoustic energy flow are presented in the paper. Spatial sampling of the field is performed by a Cartesian robot. Automatization of the measurement process is achieved with the use of a specialized control system. The method is based on measuring the sound pressure (scalar) and particle velocity (vector) quantities. The aim of the...
-
Quantitative Analysis of Biofilm Formed on Vascular Prostheses by Staphylococcus Epidermidis with Different ica and aap Genetic Status
PublikacjaOBJECTIVES: This study aims to examine biofilm formed on vascular prostheses by Staphylococcus epidermidis with different ica and aap genetic status, and to evaluate the effect of antibiotic-modified prostheses on bacterial colonization. METHODS: Biofilm formation was determined using fluorescence microscopy imaging. Quantitative analysis was conducted using the biofilm coverage ratio (BCR) calculations. RESULTS: Our investigations...
-
AUTOMATED NEGOTIATIONS OVER COLLABORATION PROTOCOL AGREEMENTS
PublikacjaThe dissertation focuses on the augmentation of proactive document - agents with built-in intelligence to recognize execution context provided by devices visited during a business process, and to reach collaboration agreement despite conflicting requirements. The proposed solution, based on intelligent bargaining using neural networks to improve simple multi-issue negotiation between the document and thedevice, requires practically...
-
Towards trustworthy multi‐modal motion prediction: Holistic evaluation and interpretability of outputs
Publikacja -
Start_V.AR Development and evaluation of a Seamless toolchain for innovative worker training using Virtual and Augmented Reality
ProjektyProjekt realizowany w Wydział Zarządzania i Ekonomii zgodnie z porozumieniem 01DS18034
-
Data Acquisition and Processing for GeoAI Models to Support Sustainable Agricultural Practices
PublikacjaThere are growing opportunities to leverage new technologies and data sources to address global problems related to sustainability, climate change, and biodiversity loss. The emerging discipline of GeoAI resulting from the convergence of AI and Geospatial science (Geo-AI) is enabling the possibility to harness the increasingly available open Earth Observation data collected from different constellations of satellites and sensors...
-
Federated Learning in Healthcare Industry: Mammography Case Study
PublikacjaThe paper focuses on the role of federated learning in a healthcare environment. The experimental setup involved different healthcare providers, each with their datasets. A comparison was made between training a deep learning model using traditional methods, where all the data is stored in one place, and using federated learning, where the data is distributed among the workers. The experiment aimed to identify possible challenges...
-
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
PublikacjaIn this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting. KDbased methods are successfully used in CIL, but they often struggle to regularize the model without access to exemplars of the training data from previous tasks. Our analysis reveals that this issue originates from substantial representation shifts in the teacher...
-
Cross-Lingual Knowledge Distillation via Flow-Based Voice Conversion for Robust Polyglot Text-to-Speech
PublikacjaIn this work, we introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. The proposed framework consists of 4 stages. In the first two stages, we use a VC model to convert utterances in the target locale to the voice of the target speaker. In the third stage, the converted data is combined with the linguistic features and durations...
-
g-C3N4 for Photocatalytic Degradation of Parabens: Precursors Influence, the Radiation Source and Simultaneous Ozonation Evaluation
PublikacjaGraphitic carbon nitride (g-C3N4) is a promising catalyst for contaminants of emerging concern removal applications, especially as a visible-light-driven material. In this study, g-C3N4 catalysts were effectively synthesized through a simple thermal polymerization method, using melamine, urea, and thiourea as precursors to elucidate the influence of these compounds on the final product’s photocatalytic performance. The degradation...
-
Displacements of bones during bending test of first metatarsophalangeal joint after arthrodesis with medially or dorsally positioned locking plate and lag screw.
Dane BadawczeThe Dataset contains the values of displacements of bone control points during the bending test of first metatarsophalangeal (MTP1) joint specimens after arthrodesis.
-
Horizon Europe proposals - Administrative Part
Dane BadawczeThe dataset contains data collected during the HE National Contact Point training on Oct. 12, 2022, reg. the administrative part of Horizon Europe grant proposals. The data set includes presentations concerning administrative forms of 2022 proposals and their content, including participant data; information about abstract writing, keyword choice and...
-
International Conference on Artificial Neural Networks and Genetic Algorithms
Konferencje -
International Work-Conference on Artificial and Natural Neural Networks
Konferencje -
International Conference on Computational Intelligence and Security
Konferencje -
International Joint Conference on Computational Intelligence
Konferencje -
International Workshop on Business Process Intelligence
Konferencje -
International Conference on Ubiquitous Intelligence and Computing
Konferencje