Filters
total: 2663
-
Catalog
- Publications 1859 available results
- Journals 94 available results
- Conferences 38 available results
- People 274 available results
- Projects 4 available results
- Laboratories 1 available results
- Research Teams 1 available results
- e-Learning Courses 91 available results
- Events 3 available results
- Open Research Data 298 available results
displaying 1000 best results Help
Search results for: neural architecture search
-
ARCHITECTURE AND MODERN INFORMATION TECHNOLOGIES
Journals -
Journal AR Architecture, Research
Journals -
Modeling and optimizing the removal of cadmium by Sinapis alba L. from contaminated soil via Response Surface Methodology and Artificial Neural Networks during assisted phytoremediation with sewage sludge
Publication -
Neuronowa symulacja temperatury i ciśnienia pary w upuście parowego bloku energetycznego = Neural simulation of pressure and temperature fluctuations at steam extraction of power units with steam turbine
PublicationW artykule przedstawiono metodę symulacji neuronowej dla zastosowań w diagnostyce on-line bloków energetycznych. Model neuronowy opiera się na statycznych jednokierunkowych sieciach neuronowych (SSN) oraz na danych z parowego bloku energetycznego o mocy 200 MW. SSN obliczają wartości referencyjne parametrów cieplno-przepływowych dla aktualnego obciążenia obiektu. Określono wpływ architektury sieci i danych uczących na jakość symulacji...
-
Monika Zielińska dr inż.
People -
Australian Workshop on Software Architecture
Conferences -
European Conference on Software Architecture
Conferences -
Australasian Computer Architecture Conference
Conferences -
Workshop on Computer Architecture Education
Conferences -
Agnieszka Gębczyńska-Janowicz dr hab. inż. arch.
People -
Metaheurystyki sztucznej inteligencji w wybranych grach komputerowych
PublicationW pracy omówiono trzy metaheurystyki sztucznej inteligencji, które mogą stać się źródłem inspiracji dla projektantów gier komputerowych. Pokazano, w jaki sposób zastosowano algorytm mrówkowy, algorytm genetyczny i algorytm tabu search w grach komputerowych zaprojektowanych przez studentów Politechniki Gdańskiej. W szczególności, odniesiono się do problematyki wyznaczania trajektorii przemieszczających się obiektów...
-
Deep learning for recommending subscription-limited documents
PublicationDocuments recommendation for a commercial, subscription-based online platform is important due to the difficulty in navigation through a large volume and diversity of content available to clients. However, this is also a challenging task due to the number of new documents added every day and decreasing relevance of older contents. To solve this problem, we propose deep neural network architecture that combines autoencoder with...
-
Ksenia Piątkowska dr inż. arch.
People -
International Symposium on Search Based Software Engineering
Conferences -
Architecture, Urban Planing, Interior Design
Journals -
Elżbieta Ratajczyk-Piątkowska dr hab. inż. arch.
People -
Thermal Images Analysis Methods using Deep Learning Techniques for the Needs of Remote Medical Diagnostics
PublicationRemote medical diagnostic solutions have recently gained more importance due to global demographic shifts and play a key role in evaluation of health status during epidemic. Contactless estimation of vital signs with image processing techniques is especially important since it allows for obtaining health status without the use of additional sensors. Thermography enables us to reveal additional details, imperceptible in images acquired...
-
Machine Learning Techniques in Concrete Mix Design
PublicationConcrete mix design is a complex and multistage process in which we try to find the best composition of ingredients to create good performing concrete. In contemporary literature, as well as in state-of-the-art corporate practice, there are some methods of concrete mix design, from which the most popular are methods derived from The Three Equation Method. One of the most important features of concrete is compressive strength, which...
-
Use of Daylight and Aesthetic Image of Glass Facades in Contemporary Buildings
PublicationThe paper deals with the architecture of contemporary buildings in respect to their aesthetic image created by the use of natural light. Sustainability is regarded as a principle of contemporary architecture, where daylighting is an important factor as it affects energy consumption and environmental quality of the space inside a building. Environmental awareness of architecture, however, involves a much wider and more holistic...
-
Australian Conference on Neural Networks
Conferences -
International Symposium on Neural Networks
Conferences -
World Congress on Neural Networks
Conferences -
Wojciech Targowski dr inż. arch.
People -
Detecting type of hearing loss with different AI classification methods: a performance review
PublicationHearing is one of the most crucial senses for all humans. It allows people to hear and connect with the environment, the people they can meet and the knowledge they need to live their lives to the fullest. Hearing loss can have a detrimental impact on a person's quality of life in a variety of ways, ranging from fewer educational and job opportunities due to impaired communication to social withdrawal in severe situations. Early...
-
Aleksander Piwek prof. dr hab. inż. arch.
People -
Modern Material Solutions Applied in Pediatric Facilities
PublicationNew tendencies in forming of the health services functional buildings’ systems shaped along with the emergence of caring for patient’s mental condition in medical sciences. The interior design harmonized with the medical function became an incredibly important feature. This opened up new opportunities for the architecture of health care facilities. A positive architecture’s impact on the user’s well-being is remarkably important...
-
SENSITIVITY OF PUBLIC PLACES IN GDAŃSK OSOWA DISTRICT
PublicationThis paper summarises the results of the research carried out at the University of Ljubljana, Faculty of Architecture, Slovenia, during the PhD visiting period of the first author from the Gdansk University of Technology, Poland, in the framework of the PhD course "Sensitive urban places", leaded by the second author. Focusing to the specific problems of the Gdansk Osowa district in Poland, this research develops the idea of sensitivity...
-
Karolina Życzkowska dr inż. arch.
People -
Szymon Kowalski mgr inż. arch.
PeopleResearch assistant in architectural studies of medieval and modern architecture in the Baltic Sea region. Scientifically, studies the possibilities of implementing virtual reality technology in the context of the conservation of architectural monuments and its impact on the theory of conservation, as well as the solutions for increasing the learning capabilities of architecture students.
-
Comparison of image pre-processing methods in liver segmentation task
PublicationAutomatic liver segmentation of Computed Tomography (CT) images is becoming increasingly important. Although there are many publications in this field there is little explanation why certain pre-processing methods were utilised. This paper presents a comparison of the commonly used approach of Hounsfield Units (HU) windowing, histogram equalisation, and a combination of these methods to try to ascertain what are the differences...
-
Evaluating Performance and Accuracy Improvements for Attention-OCR
PublicationIn this paper we evaluated a set of potential improvements to the successful Attention-OCR architecture, designed to predict multiline text from unconstrained scenes in real-world images. We investigated the impact of several optimizations on model’s accuracy, including employing dynamic RNNs (Recurrent Neural Networks), scheduled sampling, BiLSTM (Bidirectional Long Short-Term Memory) and a modified attention model. BiLSTM was...
-
Minimizing Distribution and Data Loading Overheads in Parallel Training of DNN Acoustic Models with Frequent Parameter Averaging
PublicationIn the paper we investigate the performance of parallel deep neural network training with parameter averaging for acoustic modeling in Kaldi, a popular automatic speech recognition toolkit. We describe experiments based on training a recurrent neural network with 4 layers of 800 LSTM hidden states on a 100-hour corpora of annotated Polish speech data. We propose a MPI-based modification of the training program which minimizes the...
-
Lifelong Learning Idea in Architectural Education
PublicationThe recent advances in IT and technology are forcing changes in the approach to educating society. In the 20th century, life-long learning was understood as educating adults in order to improve their occupational qualifications. Life-long learning allows the needs of the present-day world to be addressed through providing the individual with education at every stage of his/her life various forms. The search for a new model...
-
Retrieval of Heterogeneus Sevices in C2NIWA Repository
PublicationThe paper reviews the methods used for retrieval of information and services. The selected approaches presented in the review inspired us to build retrieval mechanisms in a system for searching the resources stored in the C2NIWA repository. We describe the architecture of the system, its functions and the surrounding subsystems to which it is related. For retrieval of C2NIWA sevices we propos three approaches based on: keyword...
-
Centropa: a journal of architecture and related arts
Journals -
Journal of Civil Engineering and Architecture Research
Journals -
ACM Transactions on Architecture and Code Optimization
Journals -
ACM International Symposium on Computer Architecture
Conferences -
Advances in Neural Information Processing Systems (Advances in Neural Information Processing Systems [NIPS])
Conferences -
Assessment of Emotional Expressions after Full-Face Transplantation
Publication -
ACM International Conference on Web Search and Data Mining
Conferences -
Musical Instrument Identification Using Deep Learning Approach
PublicationThe work aims to propose a novel approach for automatically identifying all instruments present in an audio excerpt using sets of individual convolutional neural networks (CNNs) per tested instrument. The paper starts with a review of tasks related to musical instrument identification. It focuses on tasks performed, input type, algorithms employed, and metrics used. The paper starts with the background presentation, i.e., metadata...
-
Karolina Krośnicka dr hab. inż. arch.
PeopleKarolina A. Krośnicka, Ph.D., D.Sc., Eng. Arch., is associated professor at Department of Urban Design and Regional Planning, Faculty of Architecture, Gdańsk University of Technology (Poland). For many years (1998 – 2016) she was employed at the Department of Transport and Logistics at the Faculty of Navigation at Gdynia Maritime University (Gdynia, Poland), where she was mostly involved in issues connected with seaports and port...
-
Anna Orchowska dr inż. arch.
People -
Cloning, expression, and purification of a recombinant cold-adapted β-galactosidase from antarctic bacterium Pseudoalteromonas sp. 22b
PublicationAntarktyczny szczep, gram-ujemnych bakterii Pseudoalteromonas sp. 22b, wyizolowanych z przewodu pokarmowego kryla z gatunku Thyssanoessa macrura, jest producentem wewnątrzkomórkowej zimnolubnej beta-galaktozydazy. Białko to jest homotetramerem, w którym każda z jednostek monomeru zbudowana jest z 1028 reszt aminokwasowych. Gen kodujący ten enzym został sklonowany i eksprymowany w komórkach E. coli. Następnie z zastosowaniem procedury...
-
Artificial Neural Networks in Engineering Conference
Conferences -
European Symposium on Artificial Neural Networks
Conferences -
IEEE International Conference on Neural Networks
Conferences -
International Conference on Artificial Neural Networks
Conferences -
International Conference on Neural Information Processing
Conferences