Deep neural networks represent an effective and universal model capable of solving a wide variety of tasks. This thesis is focused on three different types of deep neural networks - the multilayer perceptron, the convolutional neural network, and the deep belief network. All of the discussed network models are implemented on parallel hardware, and thoroughly tested for various choices of the network architecture and its parameters. The implemented system is accompanied by a detailed documentation of the architectural decisions and proposed optimizations. The efficiency of the implemented framework is confirmed by the results of the performed tests. A significant part of this thesis represents also additional testing of other existing frameworks which support deep neural networks. This comparison indicates superior performance to the tested rival frameworks of multilayer perceptrons and convolutional neural networks. The deep belief network implementation performs slightly better for RBM layers with up to 1000 hidden neurons, but has a noticeably inferior performance for more robust RBM layers when compared to the tested rival framework. Powered by TCPDF (www.tcpdf.org)

In recent years semantic segmentation models utilizing Convolutional Neural Networks (CNN) have seen significant success for multiple different segmentation problems. Models such as U-Net have produced promising results within the medical field for both regular 2D and volumetric imaging, rivalling some of the best classical segmentation methods. In this thesis we examined the possibility of using a convolutional neural network-based model to perform segmentation of discrete bone fragments in CT-volumes with segmentation-hints provided by a user. We additionally examined different classical segmentation methods used in a post-processing refinement stage and their effect on the segmentation quality. We compared the performance of our model to similar approaches and provided insight into how the interactive aspect of the model affected the quality of the result. We found that the combined approach of interactive segmentation and deep learning produced results on par with some of the best methods presented, provided there were adequate amount of annotated training data. We additionally found that the number of segmentation hints provided to the model by the user significantly affected the quality of the result, with convergence of the result around 8 provided hints.

A disponibilidade de conteúdo gerado por usuários em sites colaborativos de perguntas e respostas tem impulsionado o avanço de modelos de Question Answering (QA) baseados em reúso. Essa abordagem pode ser implementada por meio da tarefa de seleção de respostas (Answer Selection, AS), que consiste em encontrar a melhor resposta para uma dada pergunta em um conjunto pré-selecionado de respostas candidatas. Nos últimos anos, abordagens baseadas em vetores distribucionais e em redes neurais profundas, em particular em redes neurais convolutivas (CNNs), têm apresentado bons resultados na tarefa de AS. Contudo, a maioria dos modelos é avaliada sobre córpus de perguntas objetivas e bem formadas, contendo poucas palavras. Raramente estruturas textuais complexas são consideradas. Perguntas de consumidores, comuns em sites colaborativos, podem ser bastante complexas. Em geral, são representadas por múltiplas frases inter-relacionadas, que apresentam pouca objetividade, vocabulário leigo e, frequentemente, contêm informações em excesso. Essas características aumentam a dificuldade da tarefa de AS. Neste trabalho, propomos um modelo de seleção de respostas para perguntas de consumidores. São contribuições deste trabalho: (i) uma definição para o objeto de pesquisa perguntas de consumidores; (ii) um novo dataset desse tipo de pergunta, chamado MilkQA; e (iii) um modelo de seleção de respostas, chamado SlimRank. O MilkQA foi criado a partir de um arquivo de perguntas e respostas coletadas pelo serviço de atendimento de uma renomada instituição pública de pesquisa agropecuária (Embrapa). Anotadores guiados pela definição de perguntas de consumidores proposta neste trabalho selecionaram 2,6 mil pares de perguntas e respostas contidas nesse arquivo. A análise dessas perguntas levou ao desenvolvimento do modelo SlimRank, que combina representação de textos na forma de grafos semânticos com arquiteturas de CNNs. O SlimRank foi avaliado no dataset MilkQA e comparado com baselines e dois modelos do estado da arte. Os resultados alcançados pelo SlimRank foram bastante superiores aos resultados dos baselines, e compatíveis com resultados de modelos do estado da arte; porém, com uma significativa redução do tempo computacional. Acreditamos que a representação de textos na forma de grafos semânticos combinada com CNNs seja uma abordagem promissora para o tratamento dos desafios impostos pelas características singulares das perguntas de consumidores. / The increasing availability of user-generated content in community Q&A sites has led to the advancement of Question Answering (QA) models that relies on reuse. Such approach can be implemented by the task of Answer Selection (AS), which consists in finding the best answer for a given question in a pre-selected pool candidate answers. Recently, good results have been achieved by AS models based on distributed word vectors and deep neural networks that are used to rank answers for a given question. Convolutinal Neural Networks (CNNs) are particularly succesful in this task. Most of the AS models are built over datasets that contains only short and objective questions expressed as interrogative sentences containing few words. Complex text structures are rarely considered. However, consumer questions may be really complex. This kind of question is the main form of seeking information in community Q&A sites, forums and customer services. Consumer questions have characteristics that increase the difficulty of the answer selection task. In general, they are composed of multiple interrelated sentences that are usually subjective, and contains laymans terms and excess of details that may be not particulary relevant. In this work, we propose an answer selection model for consumer questions. Specifically the contributions of this work are: (i) a definition for the consumer questions research object; (ii) a new dataset of this kind of question, which we call MilkQA; and (iii) an answer selection model, named SlimRank. MilkQA was created from an archive of questions and answers collected by the customer service of a well-known public agricultural research institution (Embrapa). It contains 2.6 thousand question-answer pairs selected and anonymized by human annotators guided by the definition proposed in this work. The analysis of questions in MilkQA led to the development of SlimRank, which combines semantic textual graphs with CNN architectures. SlimRank was evaluated on MilkQA and compared to baselines and two state-of-the-art answer selection models. The results achieved by our model were much higher than the baselines and comparable to the state of the art, but with significant reduction of computational time. Our results suggest that combining semantic text graphs with convolutional neural networks are a promising approach for dealing with the challenges imposed by consumer questions unique characteristics.

This master’s thesis evaluates five existing Convolutional Neural Network (CNN) models for semantic segmentation of optical microscopy images of iron ore pellets. The models are PSPNet, FC-DenseNet, DeepLabv3+, BiSeNet and GCN. The dataset used for training and evaluation contains 180 microscopy images of iron ore pellets collected from LKAB’s experimental blast furnace in Luleå, Sweden. This thesis also investigates the impact of the dataset size and data augmentation on performance. The best performing CNN model on the task was PSPNet, which had an average accuracy of 91.7% on the dataset. Simple data augmentation techniques, horizontal and vertical flipping, improved the models’ average accuracy performance with 3.4% on average. From the results in this thesis, it was concluded that there are benefits to using CNNs for analysis of iron ore pellets, with time-saving and improved analysis as the two notable areas.

Automation plays an integral role in our daily lives. From transportation to agriculture, we rely on robots and programs to assist in accomplishing tasks. Chemistry is no except with the deployment of high throughput screening and the recent machine-led reaction discovery, there is increased interest to integrate artificial intelligence and robotics beyond medicinal and synthetic organic chemistry. The addition of automation to mechanistic studies can improve the method in which reactions are understood experimentally and fundamentally. Chapter 1 introduces the basics of reaction chemistry. As we are interested in how the reaction occurs, for this work, there is a natural bias towards understanding kinetic behaviour. Chronograms obtained through mass spectrometry facilitate understanding of kinetics. The introduction of mass spectrometry in this chapter establishes the foundation of this technique for the subsequent experimental chemistry chapters. Chapter 2 investigates the reduction and subsequent oxidation of titanocene, generating a complex mixture of oxidized products. During this investigation, an interesting and rare methyl abstraction event occurred that led to the deuterium label study to understand a radical-based oxo-titanium reaction. This was made possible by Pressurized Sample Infusion Electrospray Ionization Mass Spectrometry (PSI-ESI-MS) coupled with a smartphone colorimetry technique developed herein known as ColorPixel. In Chapter 3 we explore the integration of machine learning with reaction monitoring. The attempt to classify reaction roles based on kinetic traces was done to automate the process of identifying important species in a reaction. Often there is a large amount of data from a PSI-ESI-MS experiment, but it is time-consuming to pick out the most important species. Implementing machine learning for reaction role classification can ease this process from taking three months to accomplish to one day. This chapter also outlines the development of Kendrick, an automated reaction sampler. Combined, these tools have the potential to impact reaction monitoring through robotic assistance and can speed up the process of reaction quantification through automated processing platforms to handle the streams of data. Chapter 4 starts with the implementation of a lightweight mass spectrometry library, Spectra.ly, that is suitable for any developers using python. This platform establishes a firm foundation that can enable developers to build complex programs using simple code. This chapter also describes the collaboration project PythoMS and the development process for this framework. In addition to the framework, the chapter also describes the development of two pieces of processing software: Sinatra – a cloud-ready EDESI processing platform, and AutoMRM – a cloud-based Multiple Reaction Monitoring method development web application. / Graduate

Autonomous Driving and Advance Driver Assistance Systems (ADAS) are revolutionizing the way we drive and the future of mobility. Among ADAS, Traffic Sign Classification is an important technique which assists the driver to easily interpret traffic signs on the road. In this thesis, we used the powerful combination of Image Processing and Deep Learning to pre-process and classify the traffic signs. Recent studies in Deep Learning show us how good a Convolutional Neural Network (CNN) is for image classification and there are several state-of-the-art models with classification accuracies over 99 % existing out there. This shaped our thesis to focus more on tackling the current challenges and some open-research cases. We focussed more on performance tuning by modifying the existing architectures with a trade-off between computations and accuracies. Our research areas include enhancement in low light/noisy conditions by adding Recurrent Neural Network (RNN) connections, and contribution to a universal-regional dataset with Generative Adversarial Networks (GANs). The results obtained on the test data are comparable to the state-of-the-art models and we reached accuracies above 98% after performance evaluation in different frameworks

This thesis investigates the task of estimating the pose of a hand interacting with an object from a depth image. The main contribution of this thesis is the development of our discriminative one-shot hand-object pose estimation system. To the best of our knowledge, this is the first attempt at a one-shot hand-object pose estimation system. It is a two stage system consisting of convolutional neural networks. The first stage segments the object out of the hand from the depth image. This hand-minus-object depth image is combined with the original input depth image to form a 2-channel image for use in the second stage, pose estimation. We show that using this 2-channel image produces better pose estimation performance than a single stage pose estimation system taking just the input depth map as input. We also believe that we are amongst the first to research hand-object segmentation. We use fully convolutional neural networks to perform hand-object segmentation from a depth image. We show that this is a superior approach to random decision forests for this task. Datasets were created to train our hand-object pose estimator stage and hand-object segmentation stage. The hand-object pose labels were estimated semi-automatically with a combined manual annotation and generative approach. The segmentation labels were inferred automatically with colour thresholding. To the best of our knowledge, there were no public datasets for these two tasks when we were developing our system. These datasets have been or are in the process of being publicly released.

Neural networks represent a powerful means capable of processing various multi-media data. Two applications of artificial neural networks to 3D surface models are examined in this thesis - detection of significant features in 3D data and model classification. The theoretical review of existing self-organizing neural networks is presented and followed by description of feed-forward neural networks and convolutional neural networks (CNN). A novel modification of existing model - N-dimensional convolutional neural networks (ND- CNN) - is introduced. The proposed ND-CNN model is enhanced by an existing technique for enforced knowledge representation. The developed theoretical methods are assessed on supporting experiments with scanned 3D face models. The first experiment focuses on automatic detection of significant facial features while the second experiment performs classification of the models by their gender using the CNN and ND-CNN.

abstract: In this thesis, a new approach to learning-based planning is presented where critical regions of an environment with low probability measure are learned from a given set of motion plans. Critical regions are learned using convolutional neural networks (CNN) to improve sampling processes for motion planning (MP). In addition to an identification network, a new sampling-based motion planner, Learn and Link, is introduced. This planner leverages critical regions to overcome the limitations of uniform sampling while still maintaining guarantees of correctness inherent to sampling-based algorithms. Learn and Link is evaluated against planners from the Open Motion Planning Library (OMPL) on an extensive suite of challenging navigation planning problems. This work shows that critical areas of an environment are learnable, and can be used by Learn and Link to solve MP problems with far less planning time than existing sampling-based planners. / Dissertation/Thesis / Masters Thesis Computer Science 2019

abstract: Rapid intraoperative diagnosis of brain tumors is of great importance for planning treatment and guiding the surgeon about the extent of resection. Currently, the standard for the preliminary intraoperative tissue analysis is frozen section biopsy that has major limitations such as tissue freezing and cutting artifacts, sampling errors, lack of immediate interaction between the pathologist and the surgeon, and time consuming. Handheld, portable confocal laser endomicroscopy (CLE) is being explored in neurosurgery for its ability to image histopathological features of tissue at cellular resolution in real time during brain tumor surgery. Over the course of examination of the surgical tumor resection, hundreds to thousands of images may be collected. The high number of images requires significant time and storage load for subsequent reviewing, which motivated several research groups to employ deep convolutional neural networks (DCNNs) to improve its utility during surgery. DCNNs have proven to be useful in natural and medical image analysis tasks such as classification, object detection, and image segmentation. This thesis proposes using DCNNs for analyzing CLE images of brain tumors. Particularly, it explores the practicality of DCNNs in three main tasks. First, off-the shelf DCNNs were used to classify images into diagnostic and non-diagnostic. Further experiments showed that both ensemble modeling and transfer learning improved the classifier’s accuracy in evaluating the diagnostic quality of new images at test stage. Second, a weakly-supervised learning pipeline was developed for localizing key features of diagnostic CLE images from gliomas. Third, image style transfer was used to improve the diagnostic quality of CLE images from glioma tumors by transforming the histology patterns in CLE images of fluorescein sodium-stained tissue into the ones in conventional hematoxylin and eosin-stained tissue slides. These studies suggest that DCNNs are opted for analysis of CLE images. They may assist surgeons in sorting out the non-diagnostic images, highlighting the key regions and enhancing their appearance through pattern transformation in real time. With recent advances in deep learning such as generative adversarial networks and semi-supervised learning, new research directions need to be followed to discover more promises of DCNNs in CLE image analysis. / Dissertation/Thesis / Doctoral Dissertation Neuroscience 2019