Filters
total: 3051
filtered: 2550
-
Catalog
- Publications 2550 available results
- Journals 205 available results
- Conferences 26 available results
- Publishing Houses 1 available results
- People 102 available results
- Projects 9 available results
- e-Learning Courses 74 available results
- Events 9 available results
- Open Research Data 75 available results
Chosen catalog filters
displaying 1000 best results Help
Search results for: continual learning
-
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
PublicationClass-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task. However, the experts are usually trained all at once using whole task data, which makes them all prone to forgetting and increasing computational burden. To address this limitation,...
-
Looking through the past: better knowledge retention for generative replay in continual learning
PublicationIn this work, we improve the generative replay in a continual learning setting to perform well on challenging scenarios. Because of the growing complexity of continual learning tasks, it is becoming more popular, to apply the generative replay technique in the feature space instead of image space. Nevertheless, such an approach does not come without limitations. In particular, we notice the degradation of the continually trained...
-
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
PublicationIn 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...
-
Acrodermatitis continua Hallopeau
Publication -
Hybrid model of moving or rotating continua
PublicationThe paper introduces the method of the model reduction of systems that experience a Coriolis acceleration or gyroscopic effect component. In such causes that corresponding system equations are non-self-adjoined. Modal reduced model is built up for the system without Coriolis or gyroscopic effect terms. These phenomena are next included by application of any lumping technique. Hence, the final reduced model is a hybrid one, obtained...
-
Hybrid Model of Axially Moving Continua
PublicationThe paper introduces the method of the model reduction of systems that experience a Coriolis acceleration component. It causes that system equations are non-self-adjoined. To avoid such problem modal, reduced model is built up for the system without Coriolis acceleration terms which are next included by application of any lumping technique. Hence, the final reduced model is a hybrid one, obtained by both lumping and modal methods...
-
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
-
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...
-
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,...
-
Kinedynamics of Spherical Wavefields in Fluid and Dielectric Continua
PublicationDistubances induced by physical sources in fluids or dielectrics maintain their primary character while propagating throughout either of these bi-dynamic continua. The paper defines and illustrates four sets of bi-fields based on four specific fundamental kinedynamic solutions to inhomogeneous wave equations related to quasi-point acoustic and electromagnetic sources.
-
Theoretical calculation of pKas of phosphoric (V) acidin the polarisable continuum and cluster-continuum models
PublicationW pracy oceniono dokładność modelu polaryzowalnego kontinuum (PCM) i mieszanego modelu klaster-kontinuum do przewidywania wartości trzech kolejnych stałych dysocjacji kwasu fosforowego (V). Obliczenia PCM na poziomie MP2/6-31+G(d,p) odtwarzają wartość pierwszego pKa z rozsądną niepewnością, jednak wartości kolejnych pKa obarczone są bardzo dużym błędem, nawet po podniesieniu poziomu teorii do metody zespolonej G3B3. Dopiero obliczenia...
-
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.
-
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,...
-
Software tool for modelling of mechatronic systems with elastic continua
PublicationThe paper presents a systematic computational package for modelling and analysis of complex systems composed of multiple lumped and distributed parameter subsystems. The constructed computer program enables the frequency domain analysis of a class of linear systems and to obtain reduced order model in the form of bond graph. Obtained modal bond graph can be directly exported into 20-Sim package to further processing including nonlinear...
-
Deep learning in the fog
PublicationIn the era of a ubiquitous Internet of Things and fast artificial intelligence advance, especially thanks to deep learning networks and hardware acceleration, we face rapid growth of highly decentralized and intelligent solutions that offer functionality of data processing closer to the end user. Internet of Things usually produces a huge amount of data that to be effectively analyzed, especially with neural networks, demands high...
-
Acceleration waves in the nonlinear micromorphic continuum
PublicationWithin the framework of the nonlinear elastic theory of micromorphic continua we derive the conditions for propagation of acceleration waves. An acceleration wave, also called a wave of weak discontinuity of order two, can be treated as a propagating nonmaterial surface across which the second derivatives of the placement vector and micro-distortion tensor may undergo jump discontinuities. Here we obtain the acoustic tensor for...
-
Applications of Tensor Analysis in Continuum Mechanics
PublicationA tensor field is a tensor-valued function of position in space. The use of tensor fields allows us to present physical laws in a clear, compact form. A byproduct is a set of simple and clear rules for the representation of vector differential operators such as gradient, divergence, and Laplacian in curvilinear coordinate systems. The tensorial nature of a quantity permits us to formulate transformation rules for its components...
-
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...
-
Open source solution LMS for supporting e-learning/blended learning engineers
PublicationW artykule zaprezentowano darmowe systemy zarządzania kształceniem na odległość wspomagające e-learningowe/mieszane nauczanie inżynierów. Pierwszy system TeleCAD został opracowany w ramach projektu Leonardo da Vinci (1998-2001). System TeleCAD był propozycją w projekcie V Ramowy CURE (2003-2006). W roku 2003 dzięki projektowi Leonardo da Vinci EMDEL (2001-2005) Centrum Edukacji Niestacjonarnej Politechniki Gdańskiej wybrało system...
-
Die rolle von Chats/Diskussionsforen im eLearning an einem praktischen Bespiel, Die rolle von Chats/Diskussionsforen im eLearning an einem praktischen Bespiel. A practical example of the role of chatrooms/discussion forums in e-learning.
Publication.
-
Instant Messaging als neues kommunikationsinstrumentarium in eLearning systemen
PublicationDokonano analizy mozliwości implementacji komunikatorów w platformach zdalnego nauczania. Przedstawiono możliwe rozwiązania. Przedyskutowano wady i zalety poszczególnych rozwiazań.
-
Online Learning Based on Prototypes
Publication -
Distributed Learning with Data Reduction
Publication -
Deep Learning Approaches in Histopathology
Publication -
e-Learning in Tourism Education
Publication -
Neural networks and deep learning
PublicationIn this chapter we will provide the general and fundamental background related to Neural Networks and Deep Learning techniques. Specifically, we divide the fundamentals of deep learning in three parts, the first one introduces Deep Feed Forward Networks and the main training algorithms in the context of optimization. The second part covers Convolutional Neural Networks (CNN) and discusses their main advantages and shortcomings...
-
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...
-
Machine Learning and Deep Learning Methods for Fast and Accurate Assessment of Transthoracic Echocardiogram Image Quality
PublicationHigh-quality echocardiogram images are the cornerstone of accurate and reliable measurements of the heart. Therefore, this study aimed to develop, validate and compare machine learning and deep learning algorithms for accurate and automated assessment of transthoracic echocardiogram image quality. In total, 4090 single-frame two-dimensional transthoracic echocardiogram...
-
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...
-
PUB073 Lung Cancer Screening with LDCT – Results of a Small Cohort Continual Monitoring (Pilot Silesian Study)
Publication -
Some aspects of blended-learning education
Publication -
A consensus-based approach to the distributed learning
Publication -
Prototype selection algorithms for distributed learning
Publication -
An agent-based framework for distributed learning
Publication -
Note on universal algoritms for learning theory
PublicationW 2001 Cucker i Smale zaproponowali nowe podejście do teorii uczenia się w oparciu o problematykę teorii aproksymacji.W 2005 i 2007 Bivev, Cohen, Dahmen, DeVore i Temlyakov opublikowali dwie prace z teorii uczenia się. W omawianej publikacji uogólniliśmy ich rezultaty jednocześnie upraszczając dowody.
-
Towards Scalable Simulation of Federated Learning
PublicationFederated 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...
-
Active Learning Based on Crowdsourced Data
PublicationThe paper proposes a crowdsourcing-based approach for annotated data acquisition and means to support Active Learning training approach. In the proposed solution, aimed at data engineers, the knowledge of the crowd serves as an oracle that is able to judge whether the given sample is informative or not. The proposed solution reduces the amount of work needed to annotate large sets of data. Furthermore, it allows a perpetual increase...
-
Explainable machine learning for diffraction patterns
PublicationSerial crystallography experiments at X-ray free-electron laser facilities produce massive amounts of data but only a fraction of these data are useful for downstream analysis. Thus, it is essential to differentiate between acceptable and unacceptable data, generally known as ‘hit’ and ‘miss’, respectively. Image classification methods from artificial intelligence, or more specifically convolutional neural networks (CNNs), classify...
-
E-learning in tourism and hospitality: A map
PublicationThe impact of information and communication technologies (ICT) on tourism and hospitality industries has been widely recognized and investigated as a one of the major changes within the domains in the last decade: new ways of communicating with prospective tourists and new ways of purchasing products arisen are now part of the industries’ everyday life. Poor attention has been paid so far to the role played by new media in education...
-
Structure and Randomness in Planning and Reinforcement Learning
PublicationPlanning in large state spaces inevitably needs to balance the depth and breadth of the search. It has a crucial impact on the performance of a planner and most manage this interplay implicitly. We present a novel method \textit{Shoot Tree Search (STS)}, which makes it possible to control this trade-off more explicitly. Our algorithm can be understood as an interpolation between two celebrated search mechanisms: MCTS and random...
-
Collaborative Data Acquisition and Learning Support
PublicationWith the constant development of neural networks, traditional algorithms relying on data structures lose their significance as more and more solutions are using AI rather than traditional algorithms. This in turn requires a lot of correctly annotated and informative data samples. In this paper, we propose a crowdsourcing based approach for data acquisition and tagging with support for Active Learning where the system acts as an...
-
Speech Analytics Based on Machine Learning
PublicationIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
Internet photogrammetry as a tool for e-learning
PublicationAlong with Internet development, there were interactive applications which allow for remote sensing and photogrammetric analysis. An example of an application that can provide Earth images and make it possible to measure distances in these images is Google Earth. The authors, who have experience from 2001-2015 argue that it is possible and it is important to create more advanced photogrammetric network applications. In this there...
-
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...
-
Practical Applications for Single Pill Combinations in the Cardiovascular Continuum
Publication -
Implementation of continuum damage in elasto-viscoplastic constitutive equations
PublicationW pracy opisano podstawowy wariant modelu Chaboche, oraz założenia i implementacje kontynualnego modelu zniszczenia do komercyjnego programu MES. W pracy zaprazentowano dwa podejścia zobrazowane na przykładach obliczeń numerycznych.
-
Survey of modern trends in analysis of continuum damage mechanics
PublicationW artykule dokonano szerokiego przegladu literatury z zakresu mechaniki zniszczenia izotropowego. Przedstawiono równania stosowane w opisie zniszczenia materiału.
-
An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques
Publication -
On Non-holonomic Boundary Conditions within the Nonlinear Cosserat Continuum
PublicationWithin the framework of the nonlinear micropolar elastic continuum we discuss non-holonomic kinematic boundary conditions. By non-holonomic boundary conditions we mean linear relations between virtual displacements and virtual rotations given on the boundary. Such boundary conditions can be used for modelling of complex material interactions in the vicinity of the boundaries and interfaces.
-
Numerical simulation of asphalt mixtures fracture using continuum models
PublicationThe paper considers numerical models of fracture processes of semi-circular asphalt mixture specimens subjected to three-point bending. Parameter calibration of the asphalt mixture constitutive models requires advanced, complex experimental test procedures. The highly non-homogeneous material is numerically modelled by a quasicontinuum model. The computational parameters are averaged data of the components, i.e. asphalt, aggregate...