Search
Filters
total: 1612
displaying 1000 best results Help
Search results for: weakly supervised learning
-
Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach
PublicationBreast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private...
-
Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech
PublicationWe propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced...
-
Self-Supervised Learning to Increase the Performance of Skin Lesion Classification
PublicationTo successfully train a deep neural network, a large amount of human-labeled data is required. Unfortunately, in many areas, collecting and labeling data is a difficult and tedious task. Several ways have been developed to mitigate the problem associated with the shortage of data, the most common of which is transfer learning. However, in many cases, the use of transfer learning as the only remedy is insufficient. In this study,...
-
Supervised-learning-based development of multi-bit RCS-reduced coding metasurfaces
PublicationCoding metasurfaces have been introduced as efficient tools allowing meticulous control over the electromagnetic (EM) scattering. One of their relevant application areas is radar cross section (RCS) reduction, which principally relies on the diffusion of impinging EM waves. Despite its significance, careful control of the scattering properties poses a serious challenge at the level of practical realization. This article is concerned...
-
DALSA: Domain Adaptation for Supervised Learning From Sparsely Annotated MR Images
Publication -
Interpretable deep learning approach for classification of breast cancer - a comparative analysis of multiple instance learning models
PublicationBreast cancer is the most frequent female cancer. Its early diagnosis increases the chances of a complete cure for the patient. Suitably designed deep learning algorithms can be an excellent tool for quick screening analysis and support radiologists and oncologists in diagnosing breast cancer.The design of a deep learning-based system for automated breast cancer diagnosis is not easy due to the lack of annotated data, especially...
-
Vehicle detector training with labels derived from background subtraction algorithms in video surveillance
PublicationVehicle detection in video from a miniature station- ary closed-circuit television (CCTV) camera is discussed in the paper. The camera provides one of components of the intelligent road sign developed in the project concerning the traffic control with the use of autonomous devices being developed. Modern Convolutional Neural Network (CNN) based detectors need big data input, usually demanding their manual labeling. In the presented...
-
Deep Learning Basics 2023/24
e-Learning CoursesA course about the basics of deep learning intended for students of Computer Science. It includes an introduction to supervised machine learning, the architecture of basic artificial neural networks and their training algorithms, as well as more advanced architectures (convolutional networks, recurrent networks, transformers) and regularization and optimization techniques.
-
Vident-synth: a synthetic intra-oral video dataset for optical flow estimation
Open Research DataWe introduce Vident-synth, a large dataset of synthetic dental videos with corresponding ground truth forward and backward optical flows and occlusion masks. It can be used for:
-
Poprawa jakości klasyfikacji głębokich sieci neuronowych poprzez optymalizację ich struktury i dwuetapowy proces uczenia
PublicationW 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...
-
Uczenie maszynowe do samoorganizacji systemów rozproszonych w zastosowaniach gospodarczych
PublicationW pracy omówiono uczenie maszynowe do samoorganizacji systemów rozproszonych w zastosowaniach gospodarczych ze szczególnym uwzględnieniem sieci neuronowych do predykcji finansowych oraz szacowania ratingu przedsiębiorstw. Oprócz sieci neuronowych, istotną rolę w przygotowaniu i testowaniu informatycznych systemów finansowych może pełnić programowanie genetyczne. Z tego powodu omówiono uczenie maszynowe w aplikacjach konstruowanych...
-
Deep neural networks for data analysis 24/25
e-Learning CoursesThis course covers introduction to supervised machine learning, construction of basic artificial deep neural networks (DNNs) and basic training algorithms, as well as the overview of popular DNNs architectures (convolutional networks, recurrent networks, transformers). The course introduces students to popular regularization techniques for deep models. Besides theory, large part of the course is the project in which students apply...
-
On the connected and weakly convex domination numbers
PublicationIn this paper we study relations between connected and weakly convex domination numbers. We show that in general the difference between these numbers can be arbitrarily large and we focus on the graphs for which a weakly convex domination number equals a connected domination number. We also study the influence of the edge removing on the weakly convex domination number, in particular we show that a weakly convex domination number...
-
Weakly connected Roman domination in graphs
PublicationA Roman dominating function on a graph G=(V,E) is defined to be a function f :V → {0,1,2} satisfying the condition that every vertex u for which f(u) = 0 is adjacent to at least one vertex v for which f(v)=2. A dominating set D⊆V is a weakly connected dominating set of G if the graph (V,E∩(D×V)) is connected. We define a weakly connected Roman dominating function on a graph G to be a Roman dominating function such that the set...
-
Weakly convex domination subdivision number of a graph
PublicationA set X is weakly convex in G if for any two vertices a; b \in X there exists an ab–geodesic such that all of its vertices belong to X. A set X \subset V is a weakly convex dominating set if X is weakly convex and dominating. The weakly convex domination number \gamma_wcon(G) of a graph G equals the minimum cardinality of a weakly convex dominating set in G. The weakly convex domination subdivision number sd_wcon (G) is the minimum...
-
Supervised model predictive control of wastewater treatment plant
PublicationAn optimizing control of a wastewater treatment plant (WWTP), allowing for cost savings over long time period and fulfilling effluent discharge limits at the same time, requires application of advanced control techniques. Model Predictive Control (MPC) is a very suitable control technology for a synthesis of such a truly multivariable controller that can handle constraints and accommodate model-based knowledge combined with hard...
-
Progress on Roman and Weakly Connected Roman Graphs
PublicationA graph G for which γR(G)=2γ(G) is the Roman graph, and if γwcR(G)=2γwc(G), then G is the weakly connected Roman graph. In this paper, we show that the decision problem of whether a bipartite graph is Roman is a co-NP-hard problem. Next, we prove similar results for weakly connected Roman graphs. We also study Roman trees improving the result of M.A. Henning’s A characterization of Roman trees, Discuss. Math. Graph Theory 22 (2002)....
-
Revisiting Supervision for Continual Representation Learning
Publication"In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use of the vast amounts of unlabeled data. Recent studies have highlighted the strengths of unsupervised methods, particularly self-supervised learning, in providing robust representations. The improved...
-
Weakly convex and convex domination numbers of some products of graphs
PublicationIf $G=(V,E)$ is a simple connected graph and $a,b\in V$, then a shortest $(a-b)$ path is called a $(u-v)$-{\it geodesic}. A set $X\subseteq V$ is called {\it weakly convex} in $G$ if for every two vertices $a,b\in X$ exists $(a-b)$- geodesic whose all vertices belong to $X$. A set $X$ is {\it convex} in $G$ if for every $a,b\in X$ all vertices from every $(a-b)$-geodesic belong to $X$. The {\it weakly convex domination number}...
-
Energy-Efficient Self-Supervised Technique to Identify Abnormal User Over 5G Network for E-Commerce
PublicationWithin the realm of e-commerce networks, it is frequently observed that certain users exhibit behavior patterns that differ substantially from the normative behaviors exhibited by the majority of users. The identification of these atypical individuals and the understanding of their behavioral patterns are of significant practical significance in maintaining order on e-commerce platforms. One such method for accomplishing this...
-
Energy-Efficient Self-Supervised Technique to Identify Abnormal User Over 5G Network for E-Commerce
PublicationWithin the realm of e-commerce networks, it is frequently observed that certain users exhibit behavior patterns that differ substantially from the normative behaviors exhibited by the majority of users. The identification of these atypical individuals and the understanding of their behavioral patterns are of significant practical significance in maintaining order on e-commerce platforms. One such method for accomplishing this objective...
-
Supervised Model Reference Adaptive Control of Chlorine Residuals in Water Distribution Systems
PublicationControl of integrated quality and quantity in Drinking Water Distribution Systems within recently proposed hierarchical framework is considered in the paper. A supervised nonlinear Indirect Model Reference Adaptive Controller is derived for the lower control level of the control structure to operate as the fast feedback controller of chlorine residuals in the monitored nodes. The major supervisor role is to manage switching between...
-
Similarities and Differences Between the Vertex Cover Number and the Weakly Connected Domination Number of a Graph
PublicationA vertex cover of a graph G = (V, E) is a set X ⊂ V such that each edge of G is incident to at least one vertex of X. The ve cardinality of a vertex cover of G. A dominating set D ⊆ V is a weakly connected dominating set of G if the subgraph G[D]w = (N[D], Ew) weakly induced by D, is connected, where Ew is the set of all edges having at least one vertex in D. The weakly connected domination number γw(G) of G is the minimum cardinality...
-
Weakly Hydrated Solute of Mixed Hydrophobic–Hydrophilic Nature
PublicationInfrared (IR) spectroscopy is a commonly used and invaluable tool in studies of solvation phenomena in aqueous solutions. Concurrently, density functional theory calculations and ab initio molecular dynamics simulations deliver the solvation shell picture at the molecular detail level. The mentioned techniques allowed us to gain insights into the structure and energy of the hydrogen bonding network of water molecules around methylsulfonylmethane...
-
E-learning courses
e-Learning CoursesStrona zawiera zbiór kursów prowadzonych metodą e-learning. Kursy te są skierowane do studentów I stopnia kierunku informatyka na VII semestrze profilu Bazy danych, do studentów na kierunku informatyka na II semestrze studiów II stopnia na specjalności ZAD i ISI.
-
Machine learning for PhD students
e-Learning CoursesAn introductory course in machine learning for PhD students from Department of Geotechnical and Hydraulic Engineering
-
e-Learning - user's guide for students
e-Learning Coursese-Learning - user's guide for students
-
Weakly cooperative guards in grids
PublicationW pracy autorzy zajmują się rozmieszczaniem strażników mobilnych w kratach ortogonalnych, podali wzór na minimalną liczbę strażników w kracie oraz przeanalizowali złożoność obliczeniową problemu.
-
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...
-
Deep Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Knowledge sharing and knowledge hiding in light of the mistakes acceptance component of learning culture- knowledge culture and human capital implications
PublicationPurpose: This study examines the micromechanisms of how knowledge culture fosters human capital development. Method: An empirical model was developed using the structural equation modeling method (SEM) based on a sample of 321 Polish knowledge workers employed in different industries. Findings: This study provides direct empirical evidence that tacit knowledge sharing supports human capital, whereas tacit knowledge hiding does...
-
MANAGING LEARNING PROCESS WITH E-LEARNING TOOL
PublicationThis article presents one possibility to employ Moodle, the free e-Leaning platform, to organize learning understood as a process. Behavioral approach and application to massive courses are assumed. A case study is presented, where the introduction of Moodle resulted in better student performance in homework
-
Model-free and Model-based Reinforcement Learning, the Intersection of Learning and Planning
PublicationMy doctoral dissertation is intended as the compound of four publications considering: structure and randomness in planning and reinforcement learning, continuous control with ensemble deep deterministic policy gradients, toddler-inspired active representation learning, and large-scale deep reinforcement learning costs.
-
Blended Learning Model for Computer Techniques for Students of Architecture
PublicationAbstract: The article summarizes two-year experience of implementing hybrid formula for teaching Computer Techniques at the Faculty of Architecture at the Gdansk University of Technology. Original educational e-materials, consisting of video clips, text and graphics instructions, as well as links to online resources are embedded in the university e-learning educational platform. The author discusses technical constraints associated...
-
Deep Learning: A Case Study for Image Recognition Using Transfer Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Weakly connected domination subdivision numbers
PublicationLiczba podziału krawędzi dla dominowania słabo spójnego to najmniejsza liczba krawędzi jaką należy podzielić, aby wzrosła liczba dominowania słabo wypukłego. W pracy przedstawione są własności liczby podziału krawędzi dla dominowania słabo spójnego dla różnych grafów.
-
Weakly connected domination critical graphs
PublicationPraca dotyczy niektórych klas grafów krytycznych ze względu na liczbę dominowania słabo spójnego.
-
Structure and paramagnetism in weakly correlated Y8Co5
PublicationWe report the basic physical properties of monoclinic Y8Co5 determined by means of magnetic susceptibility, electrical resistivity, and specific heat measurements. The crystal structure of Y8Co5 is monoclinic (P21/c) with lattice parameters a = 7.0582(6) Å, b = 7.2894(6) Å, c = 24.2234(19) Å, and β = 102.112(6)° as refined by using synchrotron powder x-ray diffraction data. The compound shows temperature independent paramagnetism...
-
Weakly convex and convex domination numbers.
PublicationW artykule przedstawione są nowo zdefiniowane liczby dominowania wypukłego i słabo wypukłego oraz ich porównanie z innymi liczbami dominowania. W szczególności, rozważana jest równość liczby dominowania spójnego i wypukłego dla grafów kubicznych.
-
Weakly cooperative mobile guards in grids.
PublicationProblem straży w kratach stanowi przypadek problemu minimalnego pokrycia spójnego podzbioru płaszczyzny przez pewne szczególne podzbiory. W modelu tym przyjmuje się, że strażnik porusza się wzdłuż odcinka kraty i widzi wszystkie przecinające się z nim (prostopadłe) odcinki. W rozważanym modelu współpracy zakłada się, że każdy strażnik musi być widziany przez przynajmniej jednego innego strażnika. W pracy pokazano dowód NP-zupełności...
-
On weakly dispersive multiple-trapping transport
PublicationPodano przybliżone rozwiązania równań transportu nośników ładunku dla modelu wielokrotnego pułapkowania, odnoszących się do metody czasu przelotu - przy założeniu, że większość nośników znajduje się w stanie termicznej quasi równowagi. Otrzymane rozwiązania zweryfikowano przy pomocy obliczeń metodą Monte Carlo dla wykładniczego i gaussowskiego rozkładu pułapek. Zaproponowano nową metodę wyznaczania profilu energetycznego pułapek...
-
Supervised Classification Problems–Taxonomy of Dimensions and Notation for Problems Identification
Publication -
Social learning in cluster initiatives
PublicationPurpose – The purpose of the paper is to portray social learning in cluster initiatives (CIs), namely: 1) to explore, with the lens of the communities of practice (CoPs) theory, in what ways social learning occurs in CIs; 2) to discover how various CoPs emerge and evolve in CIs to facilitate a collective journey in their learning process. Subsequently, the authors address the research questions: In what ways does social learning...
-
TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads
PublicationTensorHive is a tool for organizing work of research and engineering teams that use servers with GPUs for machine learning workloads. In a comprehensive web interface, it supports reservation of GPUs for exclusive usage, hardware monitoring, as well as configuring, executing and queuing distributed computational jobs. Focusing on easy installation and simple configuration, the tool automatically detects the available computing...
-
Some variants of perfect graphs related to the matching number, the vertex cover and the weakly connected domination number
PublicationGiven two types of graph theoretical parameters ρ and σ, we say that a graph G is (σ, ρ)- perfect if σ(H) = ρ(H) for every non-trivial connected induced subgraph H of G. In this work we characterize (γw, τ )-perfect graphs, (γw, α′)-perfect graphs, and (α′, τ )-perfect graphs, where γw(G), τ (G) and α′(G) denote the weakly connected domination number, the vertex cover number and the matching number of G, respectively. Moreover,...
-
Model szkolenia "Blended learning" z wykorzystaniem platformy Oracle I-learning.
PublicationW artykule zaproponowano modele organizacyjne szkoleń "blended learning", które pokazują możliwości współpracy firm prywatnych z instytucjami edukacyjnymi w dziedzinie e-learningu. W ramach wspólnego eksperymentu firm Oracle, Incenti S.A., WiedzaNet Sp. z o.o. oraz Centrum Edukacji Niestacjonarnej Politechniki Gdańskiej w semestrze letnim roku akademickiego 2003/2004 udostępniony będzie kurs dla studentów Wydziału Inzynierii Lądowej...
-
Weakly connected domination stable trees [online]
PublicationPraca dotyczy pełnej charakteryzacji drzew stabilnych ze względu na liczbę dominowania słabo spójnego.
-
Acoustic heating in a weakly dispersive fluid flow
PublicationZbadano specyficzną rolę dyspersyjnych własności płynu w generacji ogrzewania przez straty energii fali akustycznej. Przedstawiono ilustracje zaistniałego ogrzewania powstającego na skutek przejścia dwoch typów fal - impulsowej i stacjonarnej.
-
Strong weakly connected domination subdivisible graphs
PublicationArtykuł dotyczy wpływu podziału krawędzi na liczbę dominowania słabo spójnego. Charakteryzujemy grafy dla których podział dowolnej krawędzi zmienia liczbę dominowania słabo spójnego oraz grafy dla których podział dowolnych dwóch krawędzi powoduje zmianę liczby dominowania słabo spójnego.
-
E-learning versus traditional learning - Polish case
PublicationE-learning jest współczesnym fenomenem, który pozwala na dostęp do kształcenia i treści edukacyjnych, niezależnie od czasu i miejsca, dla każdego użytkownika. E-learnig tworzy ogromne możliwości dla uczelni akademickich, organizacji, instytucji komercyjnych i szkoleniowych, dostarczając na żądanie kształcenia i szkoleń w wirtualnym środowisku. Student może stworzyć własny plan kształcenia, dostosowując go do swojej pracy i sytuacji...