No description available.

Although generative adversarial networks (GANs) have achieved state-of-the-art results in generating realistic look- ing images, they are often parameterized by neural net- works with relatively few learnable weights compared to those that are used for discriminative tasks. We argue that this is suboptimal in a generative setting where data is of- ten entangled in high dimensional space and models are ex- pected to benefit from high expressive power. Additionally, in a generative setting, a model often needs to extrapo- late missing information from low dimensional latent space when generating data samples while in a typical discrimina- tive task, the model only needs to extract lower dimensional features from high dimensional space. We evaluate different architectures for GANs with varying model capacities using shortcut connections in order to study the impacts of the capacity on training stability and sample quality. We show that while training tends to oscillate and not benefit from additional capacity of naively stacked layers, GANs are ca- pable of generating samples with higher quality, specifically for images, samples of higher visual fidelity given proper regularization and careful balancing. / Trots att Generative Adversarial Networks (GAN) har lyckats generera realistiska bilder består de än idag av neurala nätverk som är parametriserade med relativt få tränbara vikter jämfört med neurala nätverk som används för klassificering. Vi tror att en sådan modell är suboptimal vad gäller generering av högdimensionell och komplicerad data och anser att modeller med högre kapaciteter bör ge bättre estimeringar. Dessutom, i en generativ uppgift så förväntas en modell kunna extrapolera information från lägre till högre dimensioner medan i en klassificeringsuppgift så behöver modellen endast att extrahera lågdimensionell information från högdimensionell data. Vi evaluerar ett flertal GAN med varierande kapaciteter genom att använda shortcut connections för att studera hur kapaciteten påverkar träningsstabiliteten, samt kvaliteten av de genererade datapunkterna. Resultaten visar att träningen blir mindre stabil för modeller som fått högre kapaciteter genom naivt tillsatta lager men visar samtidigt att datapunkternas kvaliteter kan öka, specifikt för bilder, bilder med hög visuell fidelitet. Detta åstadkoms med hjälp utav regularisering och noggrann balansering.

Nitride semiconductor materials have been used in a variety of applications, such as LEDs, lasers, photovoltaic cells and medical applications. If incandescent bulbs could be replaced by white GaN LEDs, they would not only provide compactness and longer lifetime, but this would also result in huge energy savings. A renewed interest in InGaN emerged recently after it was discovered that the band gap for InN is 0.7eV, instead of the previously published value of 1.9eV. Thus InGaN solid solutions cover almost the whole visible spectrum, from a band gap of 3.34eV for GaN and 0.7eV for InN. Hence, InGaN can have excellent applications for photovoltaic cells. The objective of this work was to investigate and search for new ways of synthesis of nitrides. We studied the thermodynamics and evaluated chemical compatibilities for the growth of AlN, GaN, InN and their solid solutions from metallic solvents. The compatibility between potential substrate, crucible and solvent materials and various growth atmospheres was evaluated from Gibbs free energy calculations. Most of the nitride synthesis experiments performed by other groups were at higher temperatures (around 2,000C) and pressures up to 1GPa using different growth methods. Therefore, their results could not be extrapolated to our growth system, as their growth conditions were significantly different from ours Moreover, to the best of our knowledge; no-one has ever evaluated such compatibilities by thermodynamic calculations. We used those calculations to design our experiments for further studies on nitrides. Experimentally, we encountered fewer issues such as corrosion problems than others observed with their growth procedures, because near-atmospheric pressures and temperatures not exceeding 1,000C could be used. Preliminary experiments were performed to confirm the thermodynamic computations and test the behavior of the chosen system. A suitable configuration was found that allowed to nucleate films of InGaN on the templates. Nitride templates or 'Buffer layers' were used to saturate the solution and grow the films. A relatively simpler configuration, to create a temperature gradient in the solution was used. Two templates were placed in the crucible, one at the top and the other one at the bottom. The temperature was raised to 950C and they were soaked there for 15-20hrs. After the growth the surface morphology was analyzed using an optical microscope and it was found to be entirely different for both the templates. The atoms from the top template dissolved and attached at the bottom template. This can be explained by the thermal gradient between the two templates: one at the bottom was at lower temperature than the top template, so there was diffusion from the top substrate towards the bottom one. AFM studies were carried out on the film to study the surface morphology of the top and the bottom templates. Growth hillocks having step height typically between 15 and 50 nm were observed. Such hillocks were not present on the templates before the experiment.

Improving energy efficient lighting is a necessary step in reducing energy consumption.Lighting currently consumes 17% of all U.S. residential and commercial electricity, but a report from the U.S. Office of Energy Efficiency and Renewable Energy projects that switching to LED lighting over the next 20 years will save 46% of electricity used in lighting.GaN LEDs are used for their efficient conversion of electricity to light, but improving GaN efficiency requires optically engineering the chip to extract more light.Total internal reflection limits GaN LED performance since light must approach the chip surface within 23.6° of normal to escape into air.This thesis systematically studies the effect of index of refraction, material thickness, and nano-grating period on light extraction efficiency.An ITO layer is added to the LED surface to increase the critical angle of light, and standing wave analysis is used to optimize material thicknesses.When these results are combined with the best grating period, light output improves by 254% over the unmodified LED.

In this paper we outline a novel method for training a generative adversarial network based denoising model from an exclusively corrupted and unpaired dataset of images. Our model can learn without clean data or corrupted image pairs, and instead only requires that the noise distribution is able to be expressed analytically and that the noise at each pixel is independent. We utilize maximum a posteriori estimation as the underlying solution framework, optimizing over the analytically expressed noise generating distribution as the likelihood and employ the GAN as the prior. We then evaluate our method on several popular datasets of varying size and levels of corruption. Further we directly compare the numerical results of our experiments to that of the current state of the art unsupervised denoising model. While our proposed approach's experiments do not achieve a new state of the art, it provides an alternative method to unsupervised denoising and shows strong promise as an area for future research and untapped potential.

Numerous techniques for 3D face reconstruction from a single image exist, making use of large facial databases. However, they commonly encounter quality issues due to the absence of information from alternate perspectives. For example, 3D reconstruction with a single front view input data has limited realism, particularly for profile views. We have observed that multiple-view 3D face reconstruction yields higher-quality models compared to single-view reconstruction. Based on this observation, we propose a novel pipeline that combines several deep-learning methods to enhance the quality of reconstruction from a single frontal view. Our method requires only a single image (front view) as input, yet it generates multiple realistic facial viewpoints using various deep-learning networks. These viewpoints are utilized to create a 3D facial model, significantly enhancing the 3D face quality. Traditional image-space editing has limitations in manipulating content and styles while preserving high quality. However, editing in the latent space, which is the space after encoding or before decoding in a neural network, offers greater capabilities for manipulating a given photo. Motivated by the ability of neural networks to generate 2D images from an extensive database and recognizing that multi-view 3D face reconstruction outperforms single-view approaches, we propose a new pipeline. This pipeline involves latent space manipulation by first finding a latent vector corresponding to a given image using the Generative Adversarial Network (GAN) inversion method. We then search for nearby latent vectors to synthesize multiple pose images from the provided input image, aiming to enhance 3D face reconstruction. The generated images are then fed into Diffusion models, another image synthesis network, to generate their respective profile views. The Diffusion model is known for producing more realistic large-angle variations of a given object than GAN models do. Subsequently, all these images (multi-view images) are fed into an Autoencoder, a neural network designed for 3D face model predictions, to derive the 3D structure of the face. Finally, the texture of the 3D face model is combined to enhance its realism, and certain areas of the 3D shape are refined to correct any unrealistic aspects. Our experimental results validate the effectiveness and efficiency of our method in reconstructing highly accurate 3D models of human faces from a single input (front view input) image. The reconstructed models retain high visual fidelity to the original image, even without the need for a 3D database.

Point clouds are a widely used system for the collection and application of 3D data. But most timesthe data gathered is too scarce to reliably be used in any application. Therefore this thesis presentsa GAN based upsampling method within a patch based approach together with a GCN based featureextractor, in an attempt to enhance the density and reliability of point cloud data. Our approachis rigorously compared with existing methods to compare the performance. The thesis also makescorrelations between input sizes and how the quality of the inputs affects the upsampled result. TheGAN is also applied to real-world data to assess the viability of its current state, and to test how it isaffected by the interference that occurs in an unsupervised scenario.

Deep learning is increasingly becoming a viable way of classifying all types of data. Modern deep learning algorithms, such as one dimensional convolutional neural networks, have demonstrated excellent performance in classifying time series data because of the ability to identify time invariant features. A primary challenge of deep learning for time series classification is the large amount of data required for training and many application domains, such as in medicine, have challenges obtaining sufficient data. Transfer learning is a deep learning method used to apply feature knowledge from one deep learning model to another; this is a powerful tool when both training datasets are similar and offers smaller datasets the power of more robust larger datasets. This makes it vital that the best source dataset is selected when performing transfer learning and presently there is no metric for this purpose. In this thesis a metric of predicting the performance of transfer learning is proposed. To develop this metric this research will focus on classification and transfer learning for human-activity-recognition time series data. For general time series data, finding temporal relations between signals is computationally intensive using non-deep learning techniques. Rather than time-series signal processing, a neural network autoencoder was used to first transform the source and target datasets into a time independent feature space. To compare and quantify the suitability of transfer learning datasets, two metrics were examined: i) average embedded signal from each dataset was used to calculate the distance between each datasets centroid, and ii) a Generative Adversarial Network (GAN) model was trained and the discriminator portion of the GAN is then used to assess the dissimilarity between source and target. This thesis measures a correlation between the distance between two dataset and their similarity, as well as the ability for a GAN to discriminate between two datasets and their similarity. The discriminator metric, however, does suffer from an upper limit of dissimilarity. These metrics were then used to predict the success of transfer learning from one dataset to another for the purpose of general time series classification. / Thesis / Master of Applied Science (MASc) / Over the past decade, advances in computational power and increases in data quantity have made deep learning a useful method of complex pattern recognition and classification in data. There is a growing desire to be able to use these complex algorithms on smaller quantities of data. To achieve this, a deep learning model is first trained on a larger dataset and then retrained on the smaller dataset; this is called transfer learning. For transfer learning to be effective, there needs to be a level of similarity between the two datasets so that properties from larger dataset can be learned and then refined using the smaller dataset. Therefore, it is of great interest to understand what level of similarity exists between the two datasets. The goal of this research is to provide a similarity metric between two time series classification datasets so that potential performance gains from transfer learning can be better understood. The measure of similarity between two time series datasets presents a unique challenge due to the nature of this data. To address this challenge an encoder approach was implemented to transform the time series data into a form where each signal example can be compared against one another. In this thesis, different similarity metrics were evaluated and correlated to the performance of a deep learning model allowing the prediction of how effective transfer learning may be when applied.

No description available.

No description available.