No description available.

Interdisciplinary research is often at the core of scientific progress. This dissertation explores some advantageous synergies between machine learning, cognitive science and neuroscience. In particular, this thesis focuses on vision and images. The human visual system has been widely studied from both behavioural and neuroscientific points of view, as vision is the dominant sense of most people. In turn, machine vision has also been an active area of research, currently dominated by the use of artificial neural networks. This work focuses on learning representations that are more aligned with visual perception and the biological vision. For that purpose, I have studied tools and aspects from cognitive science and computational neuroscience, and attempted to incorporate them into machine learning models of vision. A central subject of this dissertation is data augmentation, a commonly used technique for training artificial neural networks to augment the size of data sets through transformations of the images. Although often overlooked, data augmentation implements transformations that are perceptually plausible, since they correspond to the transformations we see in our visual world–changes in viewpoint or illumination, for instance. Furthermore, neuroscientists have found that the brain invariantly represents objects under these transformations. Throughout this dissertation, I use these insights to analyse data augmentation as a particularly useful inductive bias, a more effective regularisation method for artificial neural networks, and as the framework to analyse and improve the invariance of vision models to perceptually plausible transformations. Overall, this work aims to shed more light on the properties of data augmentation and demonstrate the potential of interdisciplinary research.

Cities plan to revitalize sustainable transportation, with a key emphasis on cycling. However, cities need to provide safe environments for cyclists through better infrastru.cture design. education programs, or other interventions to increase cycling nwnbers, as safety concerns greatly discourage people from cycling. Thus, cities' strategies aim to protect and improve the safety ofthose who cycle. Here, cycling research con1ributes to understanding cycling and what factors related to the individua4 the bicycle, and the surrounding environm.ent, in.fluence the risk. cyclists face. Objective cycling safety goals are to i) decrease the outcome severity of accidents involving cyclists and ii) decrease the overall nwnber of accidents. lt is often based on accident records or police reports, yet most incidents are often not reported. Nevertheless, accident statistics are vital because they allow for factors such as demographic data and built environment tobe analyzed to understand cyclists' risk. ofbeing involved or injured in an accident. There is a worldwide need for more data about cycling accidents, their context, and the built environm.ent's influence. Hence complete datasets are required. We mak:e use of CYCLANDS - a collection of 30 datasets comprising 1.58M cycling accident records - to explore how other data and analysis can complement accident records. Thus, a subset of CYCLANDS was augmented to analyze circulation spaces around accident locations. We hope this takes a step in that direction, fostering the mix of authoritative and volunteered data and providing a more complete data set.

During the last few years, deep learning-based techniques have made much progress in the medical image processing field, such as segmentation and registration. The main characteristic of these methods is the large demand of medical images to do model training. However, the acquisition of these data is often difficult, due to the high expense and ethical issues. As a consequence, the lack of data may lead to poor performance and overfitting. To tackle this problem, we propose a data augmentation algorithm in this paper to inpaint the tumor on healthy pediatric brain MRI images to simulate pathological images. Since the growth of tumor may cause deformation and edema of the surrounding tissues which is called the 'mass effect', a probabilistic UNet is applied to mimic this deformation field. Then, instead of directly adding the tumor to the image, the GAN-based method is applied to transfer the mask to the image and make it more plausible, both visually and anatomically. Meanwhile, the annotations of the different brain tissues are also obtained by employing the deformation field to the original labels. Finally, the synthesized image together with the real dataset is trained to do the tumor segmentation task, and the results indicate a statistical improvement in accuracy.

Behovet av tillförlitliga, motståndskraftiga, och beständiga system är uppenbart i vårt samhälle, som i ökande grad blir allt mer beroende av mjukvarulösningar. För att uppnå tillfredsställande nivåer av säkerhet och robusthet måste alla system kontinuerligt genomgå tester. En av de största utmaningarna vid automatisering av programvarutestning är avsaknaden av tillförlitliga orakel kapabla att ge korrekta bedömningar av testfall. Metamorfisk testning är en metod som har visats möjlig att applicera för automatisering av testning, men som däremot kräver identifiering av metamorfiska relationer. Det har gjorts försök att identifiera metamorfiska relationer med hjälp av vissa maskininlärningsmodellers förmåga till mönsterigenkänning. Ett stort problem för sådana tillvägagångssätt är mängden tillgängliga och användbara data som dessa ML-modeller kan tränas på. Det huvudsakliga bidraget denna uppsats levererar är en automatiserad metod för att genomföra utökning av data genom källkodsmutation i syfte att skala befintliga datamängder. Specifikt behandlar denna uppsats producering av icke-ekvivalenta mutanter och deras inverkan på maskininlärningsassisterad identifiering av metamorfiska relationer. Resultaten visar att icke-ekvivalenta mutanter kan genereras effektivt, även om manuell granskning är nödvändig för att härleda korrekta etiketter för varje datapunkt. Det visas också att icke-ekvivalenta mutanter kan påverka klassificeringsprestandan positivt i vissa fall, även om resultaten varierar beroende på mutationsoperator och behandlad metamorfisk relation. Framgångsrika framsteg inom testautomatisering kan potentiellt påverka nuvarande standarder för programvaruutveckling genom att förbättra programvarutestningspraxis. Därmed bidrar denna studie till diskussionen om hur automatiserad programvarutestning kan påverka organisationens prestationsförmåga i ett bredare perspektiv. Diskussionen baseras på ramverket för balanserade styrkort, och slutsatsen visar att testautomatisering kan generera fördelaktiga resultat på flera fronter. Det är dock viktigt att samordna sådana initiativ med organisationens strategiska inriktning och långsiktiga mål. / The need for reliable, resilient, and persistent systems is evident in our society, which is becoming increasingly more dependent on software solutions. In order to achieve satisfactory levels of security and robustness, all systems continuously need to undergo testing to detect faults and unwanted functionality. One of the mayor issues in automating software testing is the lack of reliable oracles capable of deriving test case verdicts. Metamorphic testing has been identified as a testing technique which can be used for test automation, though it requires the identification of metamorphic relations. There have been attempts at identifying metamorphic relations using the pattern recognition capabilities of certain machine learning models. A significant problem for any such approach is obtaining a sufficiently large labeled dataset which the ML models can be trained on. The main contribution of this paper is an automated approach to performing data augmentation through a process of source code mutation with the aim of scaling existing datasets. Specifically, this paper considers the generation of non-equivalent mutants and their impact on machine learning assisted identification of metamorphic relations. The results show that non-equivalent mutants can be efficiently generated, although manual oversight is necessary to derive accurate labels for each sample. It is also shown that non-equivalent mutants can positively impact the classification performance in certain instances, though results vary depending mutation operator and considered metamorphic relation. Furthermore, successful advances in the area of test automation can potentially affect current software development standards by improving software testing practices. As such, this study adds to the discussion on how automated software testing might affect organizational performance. The discussion is based on the balanced scorecard framework, and the discussion concludes that test automation can generate beneficial performance outcomes. However, it is imperative to aligning such endeavours with the strategic direction and long-term objectives of the organization.

Task-oriented dialogue (ToD) systems need to interpret the user's input to understand the user's needs (intent) and corresponding relevant information (slots). This process is performed by a Natural Language Understanding (NLU) component, which maps the text utterance into a semantic frame representation, involving two subtasks: intent classification (text classification) and slot filling (sequence tagging). Typically, new domains and languages are regularly added to the system to support more functionalities. Collecting domain-specific data and performing fine-grained annotation of large amounts of data every time a new domain and language is introduced can be expensive. Thus, developing an NLU model that generalizes well across domains and languages with less labeled data (low-resource) is crucial and remains challenging. This thesis focuses on investigating transfer learning and data augmentation methods for low-resource NLU in ToD. Our first contribution is a study of the potential of non-conversational text as a source for transfer. Most transfer learning approaches assume labeled conversational data as the source task and adapt the NLU model to the target task. We show that leveraging similar tasks from non-conversational text improves performance on target slot filling tasks through multi-task learning in low-resource settings. Second, we propose a set of lightweight augmentation methods that apply data transformation on token and sentence levels through slot value substitution and syntactic manipulation. Despite its simplicity, the performance is comparable to deep learning-based augmentation models, and it is effective on six languages on NLU tasks. Third, we investigate the effectiveness of domain adaptive pre-training for zero-shot cross-lingual NLU. In terms of overall performance, continued pre-training in English is effective across languages. This result indicates that the domain knowledge learned in English is transferable to other languages. In addition to that, domain similarity is essential. We show that intermediate pre-training data that is more similar – in terms of data distribution – to the target dataset yields better performance.

This study is dedicated to enhancing the effectiveness of Optical Character Recognition (OCR) systems, with a special emphasis on Arabic handwritten digit recognition. The choice to focus on Arabic handwritten digits is twofold: first, there has been relatively less research conducted in this area compared to its English counterparts; second, the recognition of Arabic handwritten digits presents more challenges due to the inherent similarities between different Arabic digits.OCR systems, engineered to decipher both printed and handwritten text, often face difficulties in accurately identifying low-quality or distorted handwritten text. The quality of the input image and the complexity of the text significantly influence their performance. However, data augmentation strategies can notably improve these systems' performance. These strategies generate new images that closely resemble the original ones, albeit with minor variations, thereby enriching the model's learning and enhancing its adaptability. The research found Conditional Variational Autoencoders (C-VAE) and Conditional Generative Adversarial Networks (C-GAN) to be particularly effective in this context. These two generative models stand out due to their superior image generation and feature extraction capabilities. A significant contribution of the study has been the formulation of the Synthetic Image Evaluation Procedure, a systematic approach designed to evaluate and amplify the generative models' image generation abilities. This procedure facilitates the extraction of meaningful features, computation of the Fréchet Inception Distance (LFID) score, and supports hyper-parameter optimization and model modifications.

One of every eight women will in their lifetime suffer from breast cancer, making it the most common type of cancer for women. A successful treatment is very much dependent on identifying metastatic tissue which is cancer found beyond the initial tumour. Using deep learning within biomedical analysis has become an effective approach. However, its success is very dependent on large datasets. Data augmentation is a way to enhance datasets without requiring more annotated data. One way of doing this is using the cutout method which masks parts of an input image. Our research focused on investigating how the cutout method could improve the performance of Convolutional Neural Networks for classifying metastatic tissue on the Patch Camelyon dataset. Our research showed that improvements in performance can be achieved by using the cutout method. Further, our research suggests that using a non label- preserving version of cutout is better than a label- preserving version. The most improvement in accuracy was seen when we used a randomly sized cutout mask. The experiment resulted in an increase in accuracy by 3.6%, from the baseline of 82,3% to 85.9%. The cutout method was also compared- and used in conjunction with other well- established data augmentation techniques. Our conclusion is that cutout can be a competitive form of data augmentation that can be used both with and without other data augmentation techniques. / Var åttonde kvinna drabbas under sin livstid av bröstcancer. Detta gör det till den vanligaste formen av cancer för kvinnor. En framgångsrik behandling är beroende av att kunna identifiera metastatisk vävnad, vilket är cancer som spridit sig bortom den ursprungliga tumören. Att använda djupinlärning inom biomedicinsk analys har blivit en effektiv metod. Dock är dess framgång väldigt beroende av stora datamängder. Dataförstärkning är olika sätt att förbättra en mängd data som inte innebär att addera ytterligare annoterad data. Ett sätt att göra detta är genom den en metod som kallas Cutout som maskar en del av en bild. Vår studie undersöker hur Cutout påverkar resultatet när Convolutional Neural Networks klassificerar huruvida bilder från datasetet Patch Camelyon innehåler metastaser eller inte. Vår studie visar att användandet av Cutout kan innebära förbättringar i resultatet. Dessutom tyder vår studie på att resultatet förbättras än mer om även delen av bilden som kan innehålla metastaser kan maskas ut. Den största förbättringen i resultatet var när maskningen var av varierande storlek från bild till bild. Resultatet förbättrades från 82.3% korrekta klassifikationer utan någon dataförstärkning till 85.9% med den bästa versionen av Cutout. Cutout jämfördes också, och användas tillsammans med, andra väletablerade dataförstärkningsmetoder. Vår slutsats är att Cutout är en dataförstärkningsmetod med potentital att vara användbar såväl med som utan andra dataförstärkningsmetoder.

No description available.

No description available.