Search

Your search keyword '"de Jong, Edwin"' showing total 297 results
Start Over Author "de Jong, Edwin"
297 results on '"de Jong, Edwin"'

2. Towards Large-Scale Training of Pathology Foundation Models

Author

ai, kaiko., Aben, Nanne, de Jong, Edwin D., Gatopoulos, Ioannis, Känzig, Nicolas, Karasikov, Mikhail, Lagré, Axel, Moser, Roman, van Doorn, Joost, and Tang, Fei

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Driven by the recent advances in deep learning methods and, in particular, by the development of modern self-supervised learning algorithms, increased interest and efforts have been devoted to build foundation models (FMs) for medical images. In this work, we present our scalable training pipeline for large pathology imaging data, and a comprehensive analysis of various hyperparameter choices and training techniques for building pathology FMs. We release and make publicly available the first batch of our pathology FMs (https://github.com/kaiko-ai/towards_large_pathology_fms) trained on open-access TCGA whole slide images, a commonly used collection of pathology images. The experimental evaluation shows that our models reach state-of-the-art performance on various patch-level downstream tasks, ranging from breast cancer subtyping to colorectal nuclear segmentation. Finally, to unify the evaluation approaches used in the field and to simplify future comparisons of different FMs, we present an open-source framework (https://github.com/kaiko-ai/eva) designed for the consistent evaluation of pathology FMs across various downstream tasks.

Published
2024

7. A comparison of evaluation methods in coevolution

Author

Yo, Ting-Shuo and de Jong, Edwin

Subjects
Computer Science - Neural and Evolutionary Computing, Computer Science - Machine Learning
Abstract

In this research, we compare four different evaluation methods in coevolution on the Majority Function problem. The size of the problem is selected such that evaluation against all possible test cases is feasible. Two measures are used for the comparisons, i.e., the objective fitness derived from evaluating solutions against all test cases, and the objective fitness correlation (OFC), which is defined as the correlation coefficient between subjective and objective fitness. The results of our experiments suggest that a combination of average score and weighted informativeness may provide a more accurate evaluation in coevolution. In order to confirm this difference, a series of t-tests on the preference between each pair of the evaluation methods is performed. The resulting significance is affirmative, and the tests for two quality measures show similar preference on four evaluation methods. %This study is the first time OFC is actually computed on a real problem. Experiments on Majority Function problems with larger sizes and Parity problems are in progress, and their results will be added in the final version., Comment: 8 pages, 7 figures, GECCO '07: Proceedings of the 9th annual conference on Genetic and evolutionary computation

Published
2019
Full Text
View/download PDF

8. GANGs: Generative Adversarial Network Games

Author

Oliehoek, Frans A., Savani, Rahul, Gallego-Posada, Jose, van der Pol, Elise, de Jong, Edwin D., and Gross, Roderich

Subjects
Statistics - Machine Learning, Computer Science - Computer Science and Game Theory, Computer Science - Learning
Abstract

Generative Adversarial Networks (GAN) have become one of the most successful frameworks for unsupervised generative modeling. As GANs are difficult to train much research has focused on this. However, very little of this research has directly exploited game-theoretic techniques. We introduce Generative Adversarial Network Games (GANGs), which explicitly model a finite zero-sum game between a generator ($G$) and classifier ($C$) that use mixed strategies. The size of these games precludes exact solution methods, therefore we define resource-bounded best responses (RBBRs), and a resource-bounded Nash Equilibrium (RB-NE) as a pair of mixed strategies such that neither $G$ or $C$ can find a better RBBR. The RB-NE solution concept is richer than the notion of `local Nash equilibria' in that it captures not only failures of escaping local optima of gradient descent, but applies to any approximate best response computations, including methods with random restarts. To validate our approach, we solve GANGs with the Parallel Nash Memory algorithm, which provably monotonically converges to an RB-NE. We compare our results to standard GAN setups, and demonstrate that our method deals well with typical GAN problems such as mode collapse, partial mode coverage and forgetting., Comment: 9 pages, 5 figures

Published
2017

10. ArFi speckle reduction and impact on local CDU

Author

Conley, Will, primary, Hsu, Stephen, additional, Crouse, Michael, additional, Martin, Dylan, additional, Rao, Rajasekhar, additional, Karlitskaya, Natalllia, additional, van Leuken, Dirk, additional, Baselmans, Jan, additional, van Veen, Marieke, additional, de Jong, Edwin, additional, Hepp, Birgitt, additional, Nielsen, Rasmus, additional, and Bakker, Eric, additional

Published
2024
Full Text
View/download PDF

12. Incremental Sequence Learning

Author

de Jong, Edwin D.

Subjects
Computer Science - Learning, Computer Science - Neural and Evolutionary Computing
Abstract

Deep learning research over the past years has shown that by increasing the scope or difficulty of the learning problem over time, increasingly complex learning problems can be addressed. We study incremental learning in the context of sequence learning, using generative RNNs in the form of multi-layer recurrent Mixture Density Networks. While the potential of incremental or curriculum learning to enhance learning is known, indiscriminate application of the principle does not necessarily lead to improvement, and it is essential therefore to know which forms of incremental or curriculum learning have a positive effect. This research contributes to that aim by comparing three instantiations of incremental or curriculum learning. We introduce Incremental Sequence Learning, a simple incremental approach to sequence learning. Incremental Sequence Learning starts out by using only the first few steps of each sequence as training data. Each time a performance criterion has been reached, the length of the parts of the sequences used for training is increased. We introduce and make available a novel sequence learning task and data set: predicting and classifying MNIST pen stroke sequences. We find that Incremental Sequence Learning greatly speeds up sequence learning and reaches the best test performance level of regular sequence learning 20 times faster, reduces the test error by 74%, and in general performs more robustly; it displays lower variance and achieves sustained progress after all three comparison methods have stopped improving. The other instantiations of curriculum learning do not result in any noticeable improvement. A trained sequence prediction model is also used in transfer learning to the task of sequence classification, where it is found that transfer learning realizes improved classification performance compared to methods that learn to classify from scratch., Comment: Updated version: Clarified the contribution (see abstract, intro, and conclusion); added figures to illustrate the architecture of the network and the difference between training and generation; different selection of experiments in Section 6.4; some textual edits

Published
2016

13. Making a Living between Crises and Ceremonies in Tana Toraja

Author

de Jong, Edwin B.P.

Subjects
Society & social sciences, Sociology & anthropology, bic Book Industry Communication::J Society & social sciences::JH Sociology & anthropology
Abstract

Making a Living between Crisis and Ceremonies offers an account on the practice of everyday life of the Torajan people both in the highlands of Tana Toraja (South Sulawesi, Indonesia) and elsewhere (Makassar, Jakarta, Maleisië).; Readership: All concerned with the fields of livelihoods, migration, transnationalism, decentralization, economic crisis, and anyone interested in an ethnography of a Southeast Asian highland community: the Toraja.

Published
2013
Full Text
View/download PDF

16. A dual pathway for understanding the relation between wellbeing and resilience.

Author

Riasnugrahani, Missiliana, Setiawan, Tery, de Jong, Edwin, and Takwin, Bagus

Subjects
WELL-being, CONFIRMATORY factor analysis, PSYCHOLOGICAL resilience, EVIDENCE gaps, CITIES & towns
Abstract

This study investigates the intricate connections between relational wellbeing and individual resilience, through family and community protective factors. As such, we aim to bridge an existing gap in resilience literature by examining the elements that contribute to individual resilience from a relational perspective through a random sample of slum dwellers in Indonesia. To address this research gap, we adopted White's conceptualisation of relational wellbeing and integrated Benard's perspective on individual resilience and applied them using established measures to assess the general population living in slum areas across three Indonesian cities: Bima, Manado and Pontianak. Rigorous confirmatory factor analysis were conducted to establish the validity and reliability of all employed measures. The results of the mediated-path analysis underscore the significance of family protective factors in most relationships between dimensions of relational wellbeing and individual resilience. Notably, the two mediators exhibited distinct effects: the former positively mediated the relation, while the latter demonstrated an inverted mediation effect. These findings significantly enhance our understanding of the nuanced interplay between wellbeing and resilience, particularly regarding the impact of familial and community support on individuals' ability to cope with daily life challenges, especially in disaster-prone areas. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

25. Mechanowetting:numerical and theoretical analysis of droplet dynamics on deforming surfaces

Author

de Jong, Edwin and de Jong, Edwin

Abstract

Surface tension is a well-known and widespread natural phenomenon. It can be exploited to control how fluids behave on surfaces to generate, for example, self-cleaning surfaces, but it also plays an important role in modern technology, such as microfluidic chips used in biomedical analysis. Such microfluidic chips entail an extensive network of small channels and surfaces, and require only small amounts of fluids, enabling incredibly fast and accurate (medical) analyses. To get the right fluids in the right amounts at the right place at the right time on such chips is a big technological challenge, and different techniques can be used. This dissertation presents mechanowetting, a new surface-tension driven methodology that can be used to move and mix small droplets on deformable surfaces. When a droplet is deposited on a surface and that surface can be locally deformed in a controlled manner, the deformations generate a net, surface-tension driven force, pushing the droplet in the desired direction. The mechanisms behind mechanowetting were captured theoretically and computationally, and applications of mechanowetting were demonstrated using simulations and experiments. It is anticipated that the presented findings will lead to new externally-controlled, surface-deforming actuation methods as well as new applications in future microfluidic chips.

Published
2023

26. Numerical modeling and quantification of droplet mixing using mechanowetting

Author

de Jong, Edwin, van der Klok, Mark L., den Toonder, Jaap M.J., Onck, Patrick R., de Jong, Edwin, van der Klok, Mark L., den Toonder, Jaap M.J., and Onck, Patrick R.

Abstract

Capillary forces are often found in nature to drive fluid flow, and methods have been developed aimed to exploiting these forces in microfluidic systems to move droplets or mix droplet contents. Mixing of small fluid volumes, however, is challenging due to the laminar nature of the flow. Here, we show that mechanowetting, i.e., the capillary interaction between droplets and deforming surfaces, can effectively mix droplet contents. By concentrically actuating the droplet, vortex-like flow patterns are generated that promote effective mixing. To quantify the degree of mixing, we introduce two strategies that are able to determine mixer performance independent of the initial solute distribution within a droplet, represented by single scalars derived from a matrix-based method. We compare these strategies to existing measures and demonstrate the full decoupling from the initial condition. Our results can be used to design efficient mixers, featuring mechanowetting as a new enabling technology for future droplet mixers.

Published
2023

30. Coevolutionary Principles

Author

Popovici, Elena, Bucci, Anthony, Wiegand, R. Paul, De Jong, Edwin D., Rozenberg, Grzegorz, editor, Bäck, Thomas, editor, and Kok, Joost N., editor

Published
2012
Full Text
View/download PDF

32. Evaluation and Diversity in Co-evolution

Author

van Wijngaarden, Rients P. T., de Jong, Edwin D., Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Kobsa, Alfred, Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Rudolph, Günter, editor, Jansen, Thomas, editor, Beume, Nicola, editor, Lucas, Simon, editor, and Poloni, Carlo, editor

Published
2008
Full Text
View/download PDF

34. Evolutionary Multi-agent Systems

Author

’t Hoen, Pieter J., de Jong, Edwin D., Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Yao, Xin, editor, Burke, Edmund K., editor, Lozano, José A., editor, Smith, Jim, editor, Merelo-Guervós, Juan Julián, editor, Bullinaria, John A., editor, Rowe, Jonathan E., editor, Tiňo, Peter, editor, Kabán, Ata, editor, and Schwefel, Hans-Paul, editor

Published
2004
Full Text
View/download PDF

35. Intransitivity in Coevolution

Author

de Jong, Edwin D., Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Yao, Xin, editor, Burke, Edmund K., editor, Lozano, José A., editor, Smith, Jim, editor, Merelo-Guervós, Juan Julián, editor, Bullinaria, John A., editor, Rowe, Jonathan E., editor, Tiňo, Peter, editor, Kabán, Ata, editor, and Schwefel, Hans-Paul, editor

Published
2004
Full Text
View/download PDF

36. Hierarchical Genetic Algorithms

Author

de Jong, Edwin D., Thierens, Dirk, Watson, Richard A., Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Yao, Xin, editor, Burke, Edmund K., editor, Lozano, José A., editor, Smith, Jim, editor, Merelo-Guervós, Juan Julián, editor, Bullinaria, John A., editor, Rowe, Jonathan E., editor, Tiňo, Peter, editor, Kabán, Ata, editor, and Schwefel, Hans-Paul, editor

Published
2004
Full Text
View/download PDF

37. Learning Probabilistic Tree Grammars for Genetic Programming

Author

Bosman, Peter A. N., de Jong, Edwin D., Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Yao, Xin, editor, Burke, Edmund K., editor, Lozano, José A., editor, Smith, Jim, editor, Merelo-Guervós, Juan Julián, editor, Bullinaria, John A., editor, Rowe, Jonathan E., editor, Tiňo, Peter, editor, Kabán, Ata, editor, and Schwefel, Hans-Paul, editor

Published
2004
Full Text
View/download PDF

38. The Incremental Pareto-Coevolution Archive

Author

de Jong, Edwin D., Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, and Deb, Kalyanmoy, editor

Published
2004
Full Text
View/download PDF

39. Automated Extraction of Problem Structure

Author

Bucci, Anthony, Pollack, Jordan B., de Jong, Edwin, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, and Deb, Kalyanmoy, editor

Published
2004
Full Text
View/download PDF

40. Exploiting Modularity, Hierarchy, and Repetition in Variable-Length Problems

Author

de Jong, Edwin D., Thierens, Dirk, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, and Deb, Kalyanmoy, editor

Published
2004
Full Text
View/download PDF

41. G23 peptide-mediated delivery of biodegradable nanocarriers across an in vitro blood-brain barrier model

Author

de Jong, Edwin, de Jong, Edwin, de Jong, Edwin, and de Jong, Edwin

Abstract

The blood-brain barrier (BBB) consists of brain endothelial cells that prevent the passage of potentially harmful compounds from the blood into the brain. As a consequence, the BBB greatly hampers the treatment of brain diseases by limiting the entry of therapeutics into the brain. The effective treatment of brain diseases is further precluded by the enzymatic degradation of therapeutic molecules in the blood. Applying polymersomes for the transport of a therapeutic agent across the BBB seems a promising strategy for its delivery to the brain. Drugs can be encapsulated in these spherical nanoparticles composed of polymers in order to protect the therapeutics from degradation during circulation in the blood. The surface of polymersomes can be decorated with a ligand that stimulates the uptake of the drug-loaded nanoparticle by brain endothelial cells. This thesis described the design of biodegradable polymersomes that were decorated with the G23 peptide, which is a ligand that was shown to promote the transport of different types of nanoparticles across the BBB. A filter-free BBB model was developed in order to demonstrate the distinctive capacity of the G23 peptide to transport the biodegradable polymersomes across the BBB. The results of this study suggest that G23 polymersomes have the potential to become nanocarriers that enable effective treatment of brain diseases.

Published
2020

42. Learning the Ideal Evaluation Function

Author

de Jong, Edwin D., Pollack, Jordan B., Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Cantú-Paz, Erick, editor, Foster, James A., editor, Deb, Kalyanmoy, editor, Davis, Lawrence David, editor, Roy, Rajkumar, editor, O’Reilly, Una-May, editor, Beyer, Hans-Georg, editor, Standish, Russell, editor, Kendall, Graham, editor, Wilson, Stewart, editor, Harman, Mark, editor, Wegener, Joachim, editor, Dasgupta, Dipankar, editor, Potter, Mitch A., editor, Schultz, Alan C., editor, Dowsland, Kathryn A., editor, Jonoska, Natasha, editor, and Miller, Julian, editor

Published
2003
Full Text
View/download PDF

43. Representation Development from Pareto-Coevolution

Author

de Jong, Edwin D., Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Cantú-Paz, Erick, editor, Foster, James A., editor, Deb, Kalyanmoy, editor, Davis, Lawrence David, editor, Roy, Rajkumar, editor, O’Reilly, Una-May, editor, Beyer, Hans-Georg, editor, Standish, Russell, editor, Kendall, Graham, editor, Wilson, Stewart, editor, Harman, Mark, editor, Wegener, Joachim, editor, Dasgupta, Dipankar, editor, Potter, Mitch A., editor, Schultz, Alan C., editor, Dowsland, Kathryn A., editor, Jonoska, Natasha, editor, and Miller, Julian, editor

Published
2003
Full Text
View/download PDF

44. Entangled with Mother Nature through Anthropogenic and Natural Disasters

Author

Pfister, Sina, de Jong, Edwin, Pfister, Sina, and de Jong, Edwin

Abstract

Since the turn of the twenty-first century, there has been a guiding imperative in anthropology to better understand people's entanglements with nature. This article sets out to investigate the emergence of spiritual ecologies in the Chilean town of Constitucion. Unlike most previous studies, we rethink the partial connections and entanglements of humans with nature through linking this to spirituality, environmental care and gender. By adopting a kaleidoscopic perspective, we aim to avoid a simplification or a singular representation of the (re-)entanglements with Mother Nature. Constitucion provides an excellent setting for studying contemporary changes in human-nature entanglements as compounding crises of earthquakes, tsunami and forest fires, exacerbated by extensive timber production, that have struck the town during the past decade, have led to a resurgence by a large part of the population in interpreting and expressing their relationship with Mother Nature. Through intermittent ethnographic research between 2015 and 2019, we have concluded that the entanglements with Mother Nature in Constitucion are the result of what we call Andean performative pragmatism, and the overrepresentation of women within the group of people who care for Mother Nature can be interpreted through an ecowomanist perspective that stands for the creation of social and environmental justice. As such, the findings offer a fresh and updated way to understand and interrogate the challenges confronting present-day human-nature relations in times of climate adaptation both in Chile and far beyond.

Published
2022

45. Generation and Selection of Sensory Channels

Author

de Jong, Edwin D., Steels, Luc, Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Poli, Riccardo, editor, Voigt, Hans-Michael, editor, Cagnoni, Stefano, editor, Corne, David, editor, Smith, George D., editor, and Fogarty, Terence C., editor

Published
1999
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results