While deep learning has proved to be useful in a large variety of tasks, a limitation remains of needing all classes and samples to be present at the training stage in supervised problems. This is a major issue in the field of biomedical imaging since keeping samples in the training sets consistently is often a liability. Furthermore, this issue prevents the simple updating of older models with only the new data when it is introduced, and prevents collaboration between companies. In this work, we examine an array of Continual Learning approaches to try to improve upon the baseline of the naive finetuning approach when retraining on new tasks, and achieve accuracy levels similar to the ones seen when all the data is available at the same time. Continual learning approaches with which we attempt to mitigate the problem are EWC, UCB, EWC Online, SI, MAS, CN-DPM. We explore some complex scenarios with varied classes being included in the tasks, as well as close to ideal scenarios where the sample size is balanced among the tasks. Overall, we focus on X-ray images, since they encompass a large variety of diseases, with new diseases requiring retraining. In the preferred setting, where classes are relatively balanced, we get an accuracy of 63.30 versus a baseline of 53.92 and the target score of 66.83. For the continued training on the same classes, we get an accuracy of 35.52 versus a baseline of 27.73. We also examine whether learning rate adjustments at task level improve accuracy, with some improvements for EWC Online. The preliminary results indicate that CL approaches such as EWC Online and SI could be integrated into radiography data learning pipelines to reduce catastrophic forgetting in situations where some level of sequential training ability justifies the significant computational overhead. / Även om djupinlärning har visat sig vara användbart i en mängd olika uppgifter, kvarstår en begränsning av att behöva alla klasser och prover som finns på utbildningsstadiet i övervakade problem. Detta är en viktig fråga inom området biomedicinsk avbildning eftersom det ofta är en belastning att hålla prover i träningsuppsättningarna. Dessutom förhindrar det här problemet enkel uppdatering av äldre modeller med endast nya data när de introduceras och förhindrar samarbete mellan företag. I det här arbetet undersöker vi en rad kontinuerliga inlärningsmetoder för att försöka förbättra baslinjen för den naiva finjusteringsmetoden vid omskolning på nya uppgifter och närma sig noggrannhetsnivåer som de som ses när alla data är tillgängliga samtidigt. Kontinuerliga inlärningsmetoder som vi försöker mildra problemet med inkluderar bland annat EWC, UCB, EWC Online, SI. Vi utforskar några komplexa scenarier med olika klasser som ingår i uppgifterna, samt nära idealiska scenarier där exempelstorleken balanseras mellan uppgifterna. Sammantaget fokuserar vi på röntgenbilder, eftersom de omfattar ett stort antal sjukdomar, med nya sjukdomar som kräver omskolning. I den föredragna inställningen får vi en noggrannhet på 63,30 jämfört med en baslinje på 53,92 och målpoängen på 66,83. Medan vi för den utökade träningen på samma klasser får en noggrannhet på 35,52 jämfört med en baslinje på 27,73. Vi undersöker också om justeringar av inlärningsfrekvensen på uppgiftsnivå förbättrar noggrannheten, med vissa förbättringar för EWC Online. De preliminära resultaten tyder på att CL-metoder som EWC Online och SI kan integreras i rörledningar för röntgendatainlärning för att minska katastrofal glömska i situationer där en viss nivå av sekventiell utbildningsförmåga motiverar den betydande beräkningskostnaden.

Medical doctors understaffing is becoming a compelling problem in many healthcare systems. This problem can be alleviated by utilising Computer-Aided Diagnosis (CAD) systems to substitute doctors in different tasks, for instance, histopa-thological image classification. The recent surge of deep learning has allowed CAD systems to perform this task at a very competitive performance. However, a major challenge with this task is the need to periodically update the models with new data and/or new classes or diseases. These periodical updates will result in catastrophic forgetting, as Convolutional Neural Networks typically requires the entire data set beforehand and tend to lose knowledge about old data when trained on new data. Incremental learning methods were proposed to alleviate this problem with deep learning. In this thesis, two incremental learning methods, Learning without Forgetting (LwF) and a generative rehearsal-based method, are investigated. They are evaluated on two criteria: The first, capability of incrementally adding new classes to a pre-trained model, and the second is the ability to update the current model with an new unbalanced data set. Experiments shows that LwF does not retain knowledge properly for the two cases. Further experiments are needed to draw any definite conclusions, for instance using another training approach for the classes and try different combinations of losses. On the other hand, the generative rehearsal-based method tends to work for one class, showing a good potential to work if better quality images were generated. Additional experiments are also required in order to investigating new architectures and approaches for a more stable training.

The master thesis focuses on similarities and disparities in the politics of memory related to the 'forgotten' Romani Holocaust in Slovakia and Hungary after 1989. It scrutinizes based on particular topic areas to what extent is the Romani Holocaust marginalized, excluded or integrated into the historical narratives of nation-states and whether it can be classified as a competitive or multidirectional form of memory. The reference point for the comparative discursive analysis represents the Jewish Holocaust. By employing the discourse-historical approach, the thesis attempts to identify various current or long-term strategies of instrumentalizing the Romani Holocaust in specific politics of memory. Moreover, it endeavours to find out which role can the Romani Holocaust play in forming the national identity in these states or its potential endangering.

Dans l’apprentissage fédéré, un modèle global est appris en agrégeant les mises à jour du modèle calculées à partir d’un ensemble de nœuds clients, un défi clé dans ce domaine est l’hétérogénéité des données entre les clients qui dégrade les performances du modèle. Les algorithmes d’apprentissage fédéré standard effectuent plusieurs étapes de gradient avant de synchroniser le modèle, ce qui peut amener les clients à minimiser exagérément leur propre objectif local et à s’écarter de la solution globale. Nous démontrons que dans un tel contexte, les modèles de clients individuels subissent un oubli catastrophique par rapport aux données d’autres clients et nous proposons une approche simple mais efficace qui modifie l’objectif d’entropie croisée sur une base par client en repondérant le softmax de les logits avant de calculer la perte. Cette approche protège les classes en dehors de l’ensemble d’étiquettes d’un client d’un changement de représentation brutal. Grâce à une évaluation empirique approfondie, nous démontrons que notre approche peut atténuer ce problème, en apportant une amélioration continue aux algorithmes d’apprentissage fédéré standard. Cette approche est particulièrement avantageux dans les contextes d’apprentissage fédéré difficiles les plus étroitement alignés sur les scénarios du monde réel où l’hétérogénéité des données est élevée et la participation des clients à chaque cycle est faible. Nous étudions également les effets de l’utilisation de la normalisation par lots et de la normalisation de groupe avec notre méthode et constatons que la normalisation par lots, qui était auparavant considérée comme préjudiciable à l’apprentissage fédéré, fonctionne exceptionnellement bien avec notre softmax repondéré, remettant en question certaines hypothèses antérieures sur la normalisation dans un système fédéré / In Federated Learning, a global model is learned by aggregating model updates computed from a set of client nodes, a key challenge in this domain is data heterogeneity across clients which degrades model performance. Standard federated learning algorithms perform multiple gradient steps before synchronizing the model which can lead to clients overly minimizing their own local objective and diverging from the global solution. We demonstrate that in such a setting, individual client models experience a catastrophic forgetting with respect to data from other clients and we propose a simple yet efficient approach that modifies the cross-entropy objective on a per-client basis by re-weighting the softmax of the logits prior to computing the loss. This approach shields classes outside a client’s label set from abrupt representation change. Through extensive empirical evaluation, we demonstrate our approach can alleviate this problem, providing consistent improvement to standard federated learning algorithms. It is particularly beneficial under the challenging federated learning settings most closely aligned with real world scenarios where data heterogeneity is high and client participation in each round is low. We also investigate the effects of using batch normalization and group normalization with our method and find that batch normalization which has previously been considered detrimental to federated learning performs particularly well with our re-weighted softmax, calling into question some prior assumptions about normalization in a federated setting

No description available.

No description available.

No description available.

No description available.

Cities involve several systems that work together as a network of urban relationships. These systems are in balance, and they work as a whole that articulates urban life. But what makes a city memorable and special are its events: those magical situations where the uniformity of the experience stops and something unique arise. Those are the moments where our memory is deeply engraved by a particular situation that will come back in our dreams and imaginative processes as an agent image. Four urban events — a space for film edition and writing, an urban stage, a footage archive and park, and a projection space- whose locations have been determined by a Cartesian game dictated by the Plan of Washington DC; and one common discipline, Film, will be the main focus of this research and a way of understanding the relations among Memory and its spaces, Architecture and Film in the City. Each event will respond to the particularities of its context by understanding first the sites and their relation with the city. These sites will be located in the four quadrants of Washington DC- NE, SE, SW and NW- and they will be consider as different communities that, by keeping their own idiosyncrasy, create one city. The question of urban scale as well as the concept of detail as part of an architectural cosmology will be present throughout the process of the thesis by the alternation of micro and macro analysis of each stage of the research. The question of scale will be present as well when comparing the four projects with their differences in shape and size. Characterization and monstrosity as architectural concepts will be incorporated into the project too, by understanding the role of Architecture in the city and what it wants to show or "monstrare" to its inhabitants. / Master of Architecture

Kärnkraftsindustrin är en bransch som präglas av avancerad teknik och omfattande säkerhetskrav. För att säkerställa en trygg arbetsmiljö krävs därför kontinuerlig fortbildning av medarbetarna. Syftet med denna studie var att undersöka en strålskyddsutbildning på ett svenskt kärnkraftverk och bidra med förslag på hur utbildningen kan förbättras för att minska kunskapsbortfallet över tid hos medarbetarna. För att utvärdera kunskapsbortfallet genomfördes en enkätundersökning med frågeformulär innehållandes kunskapsprov. Som grund för förbättringsförslagen intervjuades lärare som undervisar den utvalda kursen. Enkätsvaren analyserades statistiskt och intervjuerna behandlades med tematisk analys. En svag korrelation mellan kunskapsnivå och tid uppmättes men undersökningen visade även att medarbetarna hade goda teoretiska kunskaper om kursinnehållet även lång tid efter kurstillfället. Förbättringsförslag som presenteras inkluderar bland annat mer stöttning till lärarna för att säkerställa fysikalisk förståelse och bra exempel på erfarenhetsåterföring, samt utveckling av lokalerna för att stimulera samtal och mer autenticitet i det praktiska momentet. Det goda kunskapsresultatet styrker lärarnas bild av att radiologiska tillbud på kärnkraftverket förmodligen inte i första hand beror på kunskapsbrist utan snarare på andra faktorer så som attityd, stress och slarv. / The nuclear power industry is characterized by advanced technology and extensive safety requirements. Continuous training of employees must therefore ensure a safe working environment. The purpose of this study was to investigate a radiation protection training at a Swedish nuclear power plant and contribute suggestions on how the course can be improved to reduce knowledge loss over time among employees. Surveys containing a knowledge test were used to evaluate memory retention. As a basis for improvement suggestions, teachers who teach the selected course were interviewed. The surveys were statistically analyzed, and the interviews were subjected to thematic analysis. A weak correlation between knowledge level and time was measured, but the study also showed that employees had good theoretical knowledge of the course content even long after the course. Improvement suggestions presented include, among other things, more support to teachers to ensure physical understanding and good examples of experience feedback, as well as development of facilities to stimulate discussions and more authenticity in practical activities. The demonstrated proficiency level support the teachers' perception that radiological incidents at the nuclear power plant probably do not primarily result from lack of knowledge but rather from other factors such as attitude, stress, and negligence.