I en framtid där förutsägelser och beslut som tas av maskininlärningssystem överträffar människors förmåga behöver systemen att vara tolkbara för att vi skall kunna lita på och förstå dem. Vår studie utforskar världen av tolkbar maskininlärning genom att designa och undersöka artefakter. Vi genomför experiment för att utforska förklarbarhet, tolkbarhet samt tekniska utmaningar att skapa maskininlärningsmodeller för att identifiera liknande men unika objekt. Slutligen genomför vi ett användartest för att utvärdera toppmoderna förklaringsverktyg i ett direkt mänskligt sammanhang. Med insikter från dessa experiment diskuterar vi den potentiella framtiden för detta fält / In a future where predictions and decisions made by machine learning systems outperform humans we need the systems to be interpretable in order for us to trust and understand them. Our study explore the realm of interpretable machine learning through designing artifacts. We conduct experiments to explore explainability, interpretability as well as technical challenges of creating machine learning models to identify objects that appear similar to humans. Lastly, we conduct a user test to evaluate current state-of-the-art visual explanatory tools in a human setting. From these insights, we discuss the potential future of this field.

Usability testing within User Interface (UI) is a central part of assuring high-quality UIdesign that provides good user-experiences across multiple user-groups. The processof usability testing often times requires extensive collection of user feedback, preferablyacross multiple user groups, to ensure an unbiased observation of the potential designflaws within the UI design. Attaining feedback from certain user groups has shown tobe challenging, due to factors such as medical conditions that limits the possibilities ofusers to participate in the usability test. An absence of these hard-to-access groups canlead to designs that fails to consider their unique needs and preferences, which maypotentially result in a worse user experience for these individuals. In this thesis, wetry to address the current gaps within data collection of usability tests by investigatingwhether the Generative Adversarial Network (GAN) framework can be used to generatehigh-quality synthetic user interactions of a particular UI gesture across multiple usergroups. Moreover, a collection UI interaction of 2 user groups, namely the elderlyand young population, was conducted where the UI interaction at focus was thedrag-and-drop operation. The datasets, comprising of both user groups were trainedon separate GANs, both using the doppelGANger architecture, and the generatedsynthetic data were evaluated based on its diversity, how well temporal correlations arepreserved and its performance compared to the real data when used in a classificationtask. The experiment result shows that both GANs produces high-quality syntheticresemblances of the drag-and-drop operation, where the synthetic samples show bothdiversity and uniqueness when compared to the actual dataset. The synthetic datasetacross both user groups also provides similar statistical properties within the originaldataset, such as the per-sample length distribution and the temporal correlationswithin the sequences. Furthermore, the synthetic dataset shows, on average, similarperformance achievements across precision, recall and F1 scores compared to theactual dataset when used to train a classifier to distinguish between the elderly andyounger population drag-and-drop sequences. Further research regarding the use ofmultiple UI gestures, using a single GAN to generate UI interactions across multipleuser groups, and performing a comparative study of different GAN architectures wouldprovide valuable insights of unexplored potentials and possible limitations within thisparticular problem domain.

In digital pathology, hematoxylin & eosin (H&E) is a routine stain which is performed on most clinical cases and it often provides clinicians with sufficient information for diagnosis. However, when making decisions on how to guide breast cancer treatment, immunohistochemical staining of human epidermal growth factor 2 (HER2 staining) is also needed. Over-expression of the HER2 protein plays a significant role in the progression of breast cancer and is therefore important to consider during treatment planning. However, the downside of HER2 staining is that it is both time consuming and rather expensive. This thesis explores the possibility for H&E-to-HER2 stain translation using generative adversarial networks (GANs). If effective, this has the potential to reduce the costs and time spent on tissue processing while still providing clinicians with the images necessary to make a complete diagnosis. To explore this area two supervised (Pix2Pix, PyramidPix2Pix) and one unsupervised (cycleGAN) GAN structure was implemented and trained on digital pathology images from the MIST dataset. These models were trained two times, with 256x256 and 512x512 patches, to see which effect patch size has on stain translation performance as well. In addition, a methodology for evaluating the quality of the generated HER2 patches was also presented and utilized. This methodology consists of structural similarity index (SSIM) and peak signal to noise ratio (PSNR) comparison to the ground truth, and a HER2 status classification protocol. In the latter a classification tool provided by Sectra was used to assign each patch with a HER2 status of No tumor, 1+, 2+ or 3+ and the statuses of the generated patches were then compared to the statuses of the ground truths. The results show that the supervised Pyramid Pix2Pix model trained on 512x512 patches performs the best according to the SSIM and PSNR metrics. However, the unsupervised cycleGAN model shows more promising results when it comes to both visual assessment and the HER2 status classification protocol. Especially when trained on 256x256 patches for 200 epochs which gave an accuracy of 0.655, F1-score of 0.674 and MCC of 0.490. In conclusion the HER2 status classification protocol is deemed as a suitable way to evaluate H&E-to-HER2 stain translation and thereby the unsupervised method is considered to be better than the supervised. Moreover, it is also concluded that a smaller patch size result in worse translation of cellular structure for the supervised methods. Further studies should focus on incorporating HER2 status classification in the cycleGAN loss function and more extensive training runs to further improve the quality of H&E-to-HER2 stain translation.

The Generative Adversarial Network framework has shown success in implicitly modeling data distributions and is able to generate realistic samples. Its architecture is comprised of a generator, which produces fake data that superficially seem to belong to the real data distribution, and a discriminator which is to distinguish fake from genuine samples. The Noiseless Joint Plug & Play model offers an extension to the framework by simultaneously training autoencoders. This model uses a pre-trained encoder as a feature extractor, feeding the generator with global information. Using the Plug & Play network as baseline, we design a new model by adding discriminators to the Plug & Play architecture. These additional discriminators are trained to discern real and fake latent codes, which are the output of the encoder using genuine and generated inputs, respectively. We proceed to investigate whether this approach is viable. Experiments conducted for the MNIST manifold show that this indeed is the case. / Generative Adversarial Network är ett ramverk vilket implicit modellerar en datamängds sannolikhetsfördelning och är kapabel till att producera realistisk exempel. Dess arkitektur utgörs av en generator, vilken kan fabricera datapunkter liggandes nära den verkliga sannolikhetsfördelning, och en diskriminator vars syfte är att urskilja oäkta punkter från genuina. Noiseless Joint Plug & Play modellen är en vidareutveckling av ramverket som samtidigt tränar autoencoders. Denna modell använder sig utav en inlärd enkoder som förser generatorn med data. Genom att använda Plug & Play modellen som referens, skapar vi en ny modell genom att addera diskriminatorer till Plug & Play architekturen. Dessa diskriminatorer är tränade att särskilja genuina och falska latenta koder, vilka har producerats av enkodern genom att ha använt genuina och oäkta datapunkter som inputs. Vi undersöker huruvida denna metod är gynnsam. Experiment utförda för MNIST datamängden visar att så är fallet.

Cybersecurity is rapidly evolving, necessitating inventive solutions for emerging challenges. Deep Learning (DL), having demonstrated remarkable capabilities across various domains, has found a significant role within Cybersecurity. This thesis focuses on benevolent and malevolent adversaries. For the benevolent adversaries, we analyze specific applications of DL in Cybersecurity contributing to the enhancement of DL for downstream tasks. Regarding the malevolent adversaries, we explore the question of how resistant to (Cyber) attacks is DL and show vulnerabilities of specific DL-based systems. We begin by focusing on the benevolent adversaries by studying the use of a generative model called Generative Adversarial Networks (GAN) to improve the abilities of DL. In particular, we look at the use of Conditional Generative Adversarial Networks (CGAN) to generate synthetic data and address issues with imbalanced datasets in cybersecurity applications. Imbalanced classes can be a significant issue in this field and can lead to serious problems. We find that CGANs can effectively address this issue, especially in more difficult scenarios. Then, we turn our attention to using CGAN with tabular cybersecurity problems. However, visually assessing the results of a CGAN is not possible when we are dealing with tabular cybersecurity data. To address this issue, we introduce AutoGAN, a method that can train a GAN on both image-based and tabular data, reducing the need for human inspection during GAN training. This opens up new opportunities for using GANs with tabular datasets, including those in cybersecurity that are not image-based. Our experiments show that AutoGAN can achieve comparable or even better results than other methods. Finally, we shift our focus to the malevolent adversaries by looking at the robustness of DL models in the context of automatic face recognition. We know from previous research that DL models can be tricked into making incorrect classifications by adding small, almost unnoticeable changes to an image. These deceptive manipulations are known as adversarial attacks. We aim to expose new vulnerabilities in DL-based Face Verification (FV) systems. We introduce a novel attack method on FV systems, called the DodgePersonation Attack, and a system for categorizing these attacks based on their specific targets. We also propose a new algorithm that significantly improves upon a previous method for making such attacks, increasing the success rate by more than 13%.

One of the state-of-the-art highlights of deep learning in the past ten years is the introduction of generative adversarial networks (GANs), which had achieved great success in their ability to generate images comparable to real photos with minimum human intervention. These networks can generalise to a multitude of desired outputs, especially in image-to-image problems and image syntheses. This thesis proposes a computer graphics pipeline for 3D rendering by utilising generative adversarial networks (GANs). This thesis is motivated by regression models and convolutional neural networks (ConvNets) such as U-Net architectures, which can be directed to generate realistic global illumination effects, by using a semi-supervised GANs model (Pix2pix) that is comprised of PatchGAN and conditional GAN which is then accompanied by a U-Net structure. Pix2pix had been chosen for this thesis for its ability for training as well as the quality of the output images. It is also different from other forms of GANs by utilising colour labels, which enables further control and consistency of the geometries that comprises the output image. The series of experiments were carried out with laboratory created image sets, to pursue the possibility of which deep learning and generative adversarial networks can lend a hand to enhance the pipeline and speed up the 3D rendering process. First, ConvNet is applied in combination with Support Vector Machine (SVM) in order to pair 3D objects with their corresponding shadows, which can be applied in Augmenter Reality (AR) scenarios. Second, a GANs approach is presented to generate shadows for non-shadowed 3D models, which can also be beneficial in AR scenarios. Third, the possibility of generating high quality renders of image sequences from low polygon density 3D models using GANs. Finally, the possibility to enhance visual coherence of the output image sequences of GAN by utilising multi-colour labels. The results of the adopted GANs model were able to generate realistic outputs comparable to the lab generated 3D rendered ground-truth and control group output images with plausible scores on PSNR and SSIM similarity index metrices.

The aim of synthetic data generation is to provide data that is not real for cases where the use of real data is somehow limited. For example, when there is a need for larger volumes of data, when the data is sensitive to use, or simply when it is hard to get access to the real data. Traditional methods of synthetic data generation use techniques that do not intend to replicate important statistical properties of the original data. Properties such as the distribution, the patterns or the correlation between variables, are often omitted. Moreover, most of the existing tools and approaches require a great deal of user-defined rules and do not make use of advanced techniques like Machine Learning or Deep Learning. While Machine Learning is an innovative area of Artificial Intelligence and Computer Science that uses statistical techniques to give computers the ability to learn from data, Deep Learning is a closely related field based on learning data representations, which may serve useful for the task of synthetic data generation. This thesis focuses on one of the most interesting and promising innovations of the last years in the Machine Learning community: Generative Adversarial Networks. An approach for generating discrete, continuous or text synthetic data with Generative Adversarial Networks is proposed, tested, evaluated and compared with a baseline approach. The results prove the feasibility and show the advantages and disadvantages of using this framework. Despite its high demand for computational resources, a Generative Adversarial Networks framework is capable of generating quality synthetic data that preserves the statistical properties of a given dataset. / Syftet med syntetisk datagenerering är att tillhandahålla data som inte är verkliga i fall där användningen av reella data på något sätt är begränsad. Till exempel, när det finns behov av större datamängder, när data är känsliga för användning, eller helt enkelt när det är svårt att få tillgång till den verkliga data. Traditionella metoder för syntetiska datagenererande använder tekniker som inte avser att replikera viktiga statistiska egenskaper hos de ursprungliga data. Egenskaper som fördelningen, mönstren eller korrelationen mellan variabler utelämnas ofta. Dessutom kräver de flesta av de befintliga verktygen och metoderna en hel del användardefinierade regler och använder inte avancerade tekniker som Machine Learning eller Deep Learning. Machine Learning är ett innovativt område för artificiell intelligens och datavetenskap som använder statistiska tekniker för att ge datorer möjlighet att lära av data. Deep Learning ett närbesläktat fält baserat på inlärningsdatapresentationer, vilket kan vara användbart för att generera syntetisk data. Denna avhandling fokuserar på en av de mest intressanta och lovande innovationerna från de senaste åren i Machine Learning-samhället: Generative Adversarial Networks. Generative Adversarial Networks är ett tillvägagångssätt för att generera diskret, kontinuerlig eller textsyntetisk data som föreslås, testas, utvärderas och jämförs med en baslinjemetod. Resultaten visar genomförbarheten och visar fördelarna och nackdelarna med att använda denna metod. Trots dess stora efterfrågan på beräkningsresurser kan ett generativt adversarialnätverk skapa generell syntetisk data som bevarar de statistiska egenskaperna hos ett visst dataset.

In this thesis we study a perception problem in the context of autonomous driving. Specifically, we study the computer vision problem of 3D object detection, in which objects should be detected from various sensor data and their position in the 3D world should be estimated. We also study the application of Generative Adversarial Networks in domain adaptation techniques, aiming to improve the 3D object detection model's ability to transfer between different domains. The state-of-the-art Frustum-PointNet architecture for LiDAR-based 3D object detection was implemented and found to closely match its reported performance when trained and evaluated on the KITTI dataset. The architecture was also found to transfer reasonably well from the synthetic SYN dataset to KITTI, and is thus believed to be usable in a semi-automatic 3D bounding box annotation process. The Frustum-PointNet architecture was also extended to explicitly utilize image features, which surprisingly degraded its detection performance. Furthermore, an image-only 3D object detection model was designed and implemented, which was found to compare quite favourably with current state-of-the-art in terms of detection performance. Additionally, the PixelDA approach was adopted and successfully applied to the MNIST to MNIST-M domain adaptation problem, which validated the idea that unsupervised domain adaptation using Generative Adversarial Networks can improve the performance of a task network for a dataset lacking ground truth annotations. Surprisingly, the approach did however not significantly improve upon the performance of the image-based 3D object detection models when trained on the SYN dataset and evaluated on KITTI.

La thèse porte sur le développement d'architectures neuronales profondes permettant d'analyser des contenus textuels ou visuels, ou la combinaison des deux. De manière générale, le travail tire parti de la capacité des réseaux de neurones à apprendre des représentations abstraites. Les principales contributions de la thèse sont les suivantes: 1) Réseaux récurrents pour la compréhension de la parole: différentes architectures de réseaux sont comparées pour cette tâche sur leurs facultés à modéliser les observations ainsi que les dépendances sur les étiquettes à prédire. 2) Prédiction d’image et de mouvement : nous proposons une architecture permettant d'apprendre une représentation d'une image représentant une action humaine afin de prédire l'évolution du mouvement dans une vidéo ; l'originalité du modèle proposé réside dans sa capacité à prédire des images à une distance arbitraire dans une vidéo. 3) Encodeurs bidirectionnels multimodaux : le résultat majeur de la thèse concerne la proposition d'un réseau bidirectionnel permettant de traduire une modalité en une autre, offrant ainsi la possibilité de représenter conjointement plusieurs modalités. L'approche été étudiée principalement en structuration de collections de vidéos, dons le cadre d'évaluations internationales où l'approche proposée s'est imposée comme l'état de l'art. 4) Réseaux adverses pour la fusion multimodale: la thèse propose d'utiliser les architectures génératives adverses pour apprendre des représentations multimodales en offrant la possibilité de visualiser les représentations dans l'espace des images. / In this dissertation, the thesis that deep neural networks are suited for analysis of visual, textual and fused visual and textual content is discussed. This work evaluates the ability of deep neural networks to learn automatic multimodal representations in either unsupervised or supervised manners and brings the following main contributions:1) Recurrent neural networks for spoken language understanding (slot filling): different architectures are compared for this task with the aim of modeling both the input context and output label dependencies.2) Action prediction from single images: we propose an architecture that allow us to predict human actions from a single image. The architecture is evaluated on videos, by utilizing solely one frame as input.3) Bidirectional multimodal encoders: the main contribution of this thesis consists of neural architecture that translates from one modality to the other and conversely and offers and improved multimodal representation space where the initially disjoint representations can translated and fused. This enables for improved multimodal fusion of multiple modalities. The architecture was extensively studied an evaluated in international benchmarks within the task of video hyperlinking where it defined the state of the art today.4) Generative adversarial networks for multimodal fusion: continuing on the topic of multimodal fusion, we evaluate the possibility of using conditional generative adversarial networks to lean multimodal representations in addition to providing multimodal representations, generative adversarial networks permit to visualize the learned model directly in the image domain.

Ne vždy je jednoduché získání dostatečně velké a kvalitní datové sady s obrázky zřetelných artefaktů, ať už kvůli nedostatku ze strany zdroje dat nebo složitosti tvorby anotací. To platí například pro radiologii, nebo také strojírenství. Abychom mohli využít moderní uznávané metody strojového učení které se využívají pro klasifikaci, segmentaci a detekci defektů, je potřeba aby byla datová sada dostatečně velká a vyvážená. Pro malé datové sady čelíme problémům jako je přeučení a slabost dat, které způsobují nesprávnou klasifikaci na úkor málo reprezentovaných tříd. Tato práce se zabývá prozkoumáváním využití generativních sítí pro rozšíření a vyvážení datové sady o nové vygenerované obrázky. Za použití sítí typu Conditional Generative Adversarial Networks (CGAN) a heuristického generátoru anotací jsme schopni generovat velké množství nových snímků součástek s defekty. Pro experimenty s generováním byla použita datová sada závitů. Dále byly použity dvě další datové sady keramiky a snímků z MRI (BraTS). Nad těmito dvěma datovými sadami je provedeno zhodnocení vlivu generovaných dat na učení a zhodnocení přínosu pro zlepšení klasifikace a segmentace.