<p>Deep Neural Networks (DNNs) have greatly advanced the state-of-the-art in a wide range of machine learning tasks involving image, video, speech and text analytics, and are deployed in numerous widely-used products and services. Improvements in the capabilities of hardware platforms such as Graphics Processing Units (GPUs) and specialized accelerators have been instrumental in enabling these advances as they have allowed more complex and accurate networks to be trained and deployed. However, the enormous computational and memory demands of DNNs continue to increase with growing data size and network complexity, posing a continuing challenge to computing system designers. For instance, state-of-the-art image recognition DNNs require hundreds of millions of parameters and hundreds of billions of multiply-accumulate operations while state-of-the-art language models require hundreds of billions of parameters and several trillion operations to process a single input instance. Another major obstacle in the adoption of DNNs, despite their impressive accuracies on a range of datasets, has been their lack of robustness. Specifically, recent efforts have demonstrated that small, carefully-introduced input perturbations can force a DNN to behave in unexpected and erroneous ways, which can have to severe consequences in several safety-critical DNN applications like healthcare and autonomous vehicles. In this dissertation, we explore approximate computing as an avenue to improve the speed and energy efficiency of DNNs, as well as their robustness to input perturbations.</p> <p> </p> <p>Approximate computing involves executing selected computations of an application in an approximate manner, while generating favorable trade-offs between computational efficiency and output quality. The intrinsic error resilience of machine learning applications makes them excellent candidates for approximate computing, allowing us to achieve execution time and energy reductions with minimal effect on the quality of outputs. This dissertation performs a comprehensive analysis of different approximate computing techniques for improving the execution efficiency of DNNs. Complementary to generic approximation techniques like quantization, it identifies approximation opportunities based on the specific characteristics of three popular classes of networks - Feed-forward Neural Networks (FFNNs), Recurrent Neural Networks (RNNs) and Spiking Neural Networks (SNNs), which vary considerably in their network structure and computational patterns.</p> <p> </p> <p>First, in the context of feed-forward neural networks, we identify sparsity, or the presence of zero values in the data structures (activations, weights, gradients and errors), to be a major source of redundancy and therefore, an easy target for approximations. We develop lightweight micro-architectural and instruction set extensions to a general-purpose processor core that enable it to dynamically detect zero values when they are loaded and skip future instructions that are rendered redundant by them. Next, we explore LSTMs (the most widely used class of RNNs), which map sequences from an input space to an output space. We propose hardware-agnostic approximations that dynamically skip redundant symbols in the input sequence and discard redundant elements in the state vector to achieve execution time benefits. Following that, we consider SNNs, which are an emerging class of neural networks that represent and process information in the form of sequences of binary spikes. Observing that spike-triggered updates along synaptic connections are the dominant operation in SNNs, we propose hardware and software techniques to identify connections that can be minimally impact the output quality and deactivate them dynamically, skipping any associated updates.</p> <p> </p> <p>The dissertation also delves into the efficacy of combining multiple approximate computing techniques to improve the execution efficiency of DNNs. In particular, we focus on the combination of quantization, which reduces the precision of DNN data-structures, and pruning, which introduces sparsity in them. We observe that the ability of pruning to reduce the memory demands of quantized DNNs decreases with precision as the overhead of storing non-zero locations alongside the values starts to dominate in different sparse encoding schemes. We analyze this overhead and the overall compression of three different sparse formats across a range of sparsity and precision values and propose a hybrid compression scheme that identifies that optimal sparse format for a pruned low-precision DNN.</p> <p> </p> <p>Along with improved execution efficiency of DNNs, the dissertation explores an additional advantage of approximate computing in the form of improved robustness. We propose ensembles of quantized DNN models with different numerical precisions as a new approach to increase robustness against adversarial attacks. It is based on the observation that quantized neural networks often demonstrate much higher robustness to adversarial attacks than full precision networks, but at the cost of a substantial loss in accuracy on the original (unperturbed) inputs. We overcome this limitation to achieve the best of both worlds, i.e., the higher unperturbed accuracies of the full precision models combined with the higher robustness of the low precision models, by composing them in an ensemble.</p> <p> </p> <p><br></p><p>In summary, this dissertation establishes approximate computing as a promising direction to improve the performance, energy efficiency and robustness of neural networks.</p>

This paper deals with classifying objects using deep neural networks. Whole scene segmentation was used as main algorithm for the classification purpose which works with video sequences and obtains information between two video frames. Optical flow was used for getting information from the video frames, based on which features maps of a~neural network are warped. Two neural network architectures were adjusted to work with videos and experimented with. Results of the experiments show, that using videos for image segmentation improves accuracy (IoU) compared to the same architecture working with images.

<p>Automatsko prepoznavanje govora je tehnologija koja računarima<br />omogućava pretvaranje izgovorenih reči u tekst. Ona se može<br />primeniti u mnogim savremenim sistemima koji uključuju komunikaciju<br />između čoveka i mašine. U ovoj disertaciji detaljno je opisana jedna<br />od dve glavne komponente sistema za prepoznavanje govora, a to je<br />jezički model, koji specificira rečnik sistema, kao i pravila prema<br />kojim se pojedinačne reči mogu povezati u rečenicu. Srpski jezik spada<br />u grupu visoko inflektivnih i morfološki bogatih jezika, što znači<br />da koristi veći broj različitih završetaka reči za izražavanje<br />željene gramatičke, sintaksičke ili semantičke funkcije date reči.<br />Ovakvo ponašanje često dovodi do velikog broja grešaka sistema za<br />prepoznavanje govora kod kojih zbog dobrog akustičkog poklapanja<br />prepoznavač pogodi osnovni oblik reči, ali pogreši njen završetak.<br />Taj završetak može da označava drugu morfološku kategoriju, na<br />primer, padež, rod ili broj. U radu je predstavljen novi alat za<br />modelovanje jezika, koji uz identitet reči u modelu može da koristi<br />dodatna leksička i morfološka obeležja reči, čime je testirana<br />hipoteza da te dodatne informacije mogu pomoći u prevazilaženju<br />značajnog broja grešaka prepoznavača koje su posledica<br />inflektivnosti srpskog jezika.</p> / <p>Automatic speech recognition is a technology that allows computers to<br />convert spoken words into text. It can be applied in various areas which<br />involve communication between humans and machines. This thesis primarily<br />deals with one of two main components of speech recognition systems - the<br />language model, that specifies the vocabulary of the system, as well as the<br />rules by which individual words can be linked into sentences. The Serbian<br />language belongs to a group of highly inflective and morphologically rich<br />languages, which means that it uses a number of different word endings to<br />express the desired grammatical, syntactic, or semantic function of the given<br />word. Such behavior often leads to a significant number of errors in speech<br />recognition systems where due to good acoustic matching the recognizer<br />correctly guesses the basic form of the word, but an error occurs in the word<br />ending. This word ending may indicate a different morphological category, for<br />example, word case, grammatical gender, or grammatical number. The<br />thesis presents a new language modeling tool which, along with the word<br />identity, can also model additional lexical and morphological features of the<br />word, thus testing the hypothesis that this additional information can help<br />overcome a significant number of recognition errors that result from the high<br />inflectivity of the Serbian language.</p>

abstract: Object detection is an interesting computer vision area that is concerned with the detection of object instances belonging to specific classes of interest as well as the localization of these instances in images and/or videos. Object detection serves as a vital module in many computer vision based applications. This work focuses on the development of object detection methods that exhibit increased robustness to varying illuminations and image quality. In this work, two methods for robust object detection are presented. In the context of varying illumination, this work focuses on robust generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS) under varying illumination conditions. The highlight of the first method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). It is first shown that the angular distortion in the Inverse Perspective Mapping (IPM) domain belonging to obstacle edges varies as a function of their corresponding 2D location in the camera plane. This information is used to generate object proposals. A novel proposal assessment method based on fusing statistical properties from both the IPM image and the camera image to perform robust outlier elimination and false positive reduction is also proposed. In the context of image quality, this work focuses on robust multiple-class object detection using deep neural networks for images with varying quality. The use of Generative Adversarial Networks (GANs) is proposed in a novel generative framework to generate features that provide robustness for object detection on reduced quality images. The proposed GAN-based Detection of Objects (GAN-DO) framework is not restricted to any particular architecture and can be generalized to several deep neural network (DNN) based architectures. The resulting deep neural network maintains the exact architecture as the selected baseline model without adding to the model parameter complexity or inference speed. Performance results provided using GAN-DO on object detection datasets establish an improved robustness to varying image quality and a higher object detection and classification accuracy compared to the existing approaches. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2020

Quality inspections have seen varying degrees of automation depending on the complexity of the task and the environment. Especially in later phases of multi-stage manufacturing processes, such as final assembly in automotive industries, quality inspections are largely manual to this day. Today, emerging technologies offer both pressures and tools to increase automation. However, the current state of the research field is lacking in studies that help guide companies toward implementation. Thus, quality managers at final assembly for Scania's truck coachwork factory in Oskarshamn (MC) stipulated a thesis assignment to explore how inspections in their final assembly workshop could be automated. This assignment constitutes the purpose of this thesis project - to provide an exploratory study into existing and emerging technologies that enable automation of quality inspections at MC. This was eventually delimited to exploring automated visual inspection technologies. In order to better understand Scania's inspection and manufacturing system, a series of interviews and shadowings were undertaken with appropriate respondents. From these, we were able to extract seven inspection system requirements, most important were the ability to (1) handle high variability, (2) add new inspections fast, (3) inspect in direct flow and (4) inspect inside and outside of the truck coach without disassembly. Then, a thorough and comprehensive review of 559 active inspections allowed us to categorize and map the nature of inspections at MC. In our literature review, a model for a general quality inspections was found, which was used to guide and ground our proposals and recommendations as well as provided intuitive illustration. Further, two paradigms emerged as most interesting for this project: machine vision and deep learning. A theoretical comparison of the two suggested that the more traditional, rule-based machine vision algorithms would struggle in accommodating the requirements previously found. However, we could infer that deep learning would be highly suitable with respect to MC's requirements and inspections. A prototype deep learning inspection system gave further validation toward our speculations that deep learning offered the greatest potential for automation in complex environments such as MC's. Although this thesis was created for Scania as a primary customer, important theoretical and practical contributions were developed for a more general audience. Firstly, the exploration into new avenues for automation that overcome their traditional limitations were provided; something that is of high current import given the trends toward more complex manufacturing settings. Practically, we provide some guidance to industries that find themselves in similar situations to Scania - employing complex manufacturing systems or having complex products - where our findings can give insights in regards to modern automation challenges and solutions. / Kvalitetsinspektioner har automatiserats i variarande grad beroende på uppgiftens och omgivningens komlexitet. I synnerhet i de senare stadierna av flerstegsproduktioner, exempelvis slutmontering i fordonstillverkningsindustrin, består manuella inspektioner i stor utsträckning. Den snabba tekniska utvecklingen som har skett nyligen avger både ett tryck och skapar verktyg för att utöka automatiseringen. Dessvärre erbjuder dagslägets forskning föga stöd till företag gällande storskalig implementering av automatiserade kvalitetsinspektionssystem. Därför skapade kvalitetschefer på Scanias lastbilshyttmonteringsfabrik i Oskarshamn (MC) ett uppdrag att utforska hur deras inspektioner skulle kunna automatiseras. Detta uppdrag utgjorde syftet i vårt examensarbete: att utföra en explorativ studie inom befintliga och nya tekniker som möjliggör automatisering av MCs kvalitetsinpspektioner, vilket senare avgränsades till undersökandet av visuella kvalitetsinspektioner. För att tillgodogöra oss en djupare förståelse för Scanias inspektions- och produktionssytem utfördes en serie intervjuer och skuggningar med kunniga respondenter. Datan som erhölls utgjorde grunden i en nulägesanalys, från vilken sju systemkrav för ett inspektionssystem på MC kunde extraheras. De viktigaste av dessa var förmågan att (1) klara av hög variation, (2) addera nya inspektionspunkter snabbt, (3) kontrollera i direktflödet och (4) kontrollera innan- och utanför lastbilshytten. Vidare gjordes en omfattande genomgång av 559 aktiva inspektionspunkter vilket resulterade i en kategorisering och kartläggning av inspektioner på MC. I vår genomgång av relevant vetenskaplig litteratur hittades en generell modell för kvalitetskontroll som användes för att illustrera och teroretiskt förankra rekommendationer för ett automatiskt inspektionssystem. Vidare urskiljdes två intressanta områden i forskningen, machine vision och deep learning. En teoretisk jämförelse av traditionella regelbaserade machine vision algoritmer med deep learning erhöll att den förstnämnda är mindre lämpad för Scania med hänsyn till de krav som tagits fram. Deep learning å andra sidan, erbjuder många fördelar i relation till dessa. Genom en relativt enkel process kunde en deep learning baserad prototyp utvecklas. Prototypen påvisade goda resultat och gav vidare validering av vår spekulation att deep learning är ett lämpligt verktyg för automatisering i komplexa miljöer.Trots att detta examensarbete hade Scania som huvudsaklig uppdragsgivare så gjordes viktiga teoretiska och praktiska bidrag. En utforskning av i nya möjligheter för automatisering som kan överkomma begränsningarna av traditionell automatisering framtogs, vilket anses som både aktuellt och av vikt för samtiden där trender går mot mer dynamiska produktionssystem. Vad gäller praktiska bidrag så utgör denna rapport en sammanställning av råd till företag som befinner sig i liknande sitser som Scania - som använder komplexa produktionssystem eller har komplexa produkter - där våra resultat kan ge insikt gällande svårigheter och lösningar för modern automatisering.

The field of speech recognition has during the last decade left the re- search stage and found its way in to the public market. Most computers and mobile phones sold today support dictation and transcription in a number of chosen languages.  Swedish is often not one of them. In this thesis, which is executed on behalf of the Swedish Radio, an Automatic Speech Recognition model for Swedish is trained and the performance evaluated. The model is built using the open source toolkit Kaldi.  Two approaches of training the acoustic part of the model is investigated. Firstly, using Hidden Markov Model and Gaussian Mixture Models and secondly, using Hidden Markov Models and Deep Neural Networks. The later approach using deep neural networks is found to achieve a better performance in terms of Word Error Rate. / De senaste åren har olika tillämpningar inom människa-dator interaktion och främst taligenkänning hittat sig ut på den allmänna marknaden. Många system och tekniska produkter stöder idag tjänsterna att transkribera tal och diktera text. Detta gäller dock främst de större språken och sällan finns samma stöd för mindre språk som exempelvis svenskan. I detta examensprojekt har en modell för taligenkänning på svenska ut- vecklas. Det är genomfört på uppdrag av Sveriges Radio som skulle ha stor nytta av en fungerande taligenkänningsmodell på svenska. Modellen är utvecklad i ramverket Kaldi. Två tillvägagångssätt för den akustiska träningen av modellen är implementerade och prestandan för dessa två är evaluerade och jämförda. Först tränas en modell med användningen av Hidden Markov Models och Gaussian Mixture Models och slutligen en modell där Hidden Markov Models och Deep Neural Networks an- vänds, det visar sig att den senare uppnår ett bättre resultat i form av måttet Word Error Rate.

During the recent years, numerous so-called Buy Now, Pay Later companies have emerged. A type of financial institution offering short term consumer credit contracts. As these institutions have gained popularity, their undertaken credit risk has increased vastly. Simultaneously, the IFRS 9 regulatory requirements must be complied with. Specifically, the Probability of Default (PD) for the entire lifetime of such a contract must be estimated. The collection of incremental PDs over the entire course of the contract is called the PD term structure. Accurate estimates of the PD term structures are desirable since they aid in steering business decisions based on a given risk appetite, while staying compliant with current regulations. In this thesis, the efficiency of Machine Learning within PD term structure modeling is examined. Two categories of Machine Learning algorithms, in five variations each, are evaluated; (1) Deep Neural Networks; and (2) Gradient Boosted Trees. The Machine Learning models are benchmarked against a traditional Markov Chain model. The performance of the models is measured by a set of calibration and discrimination metrics, evaluated at each time point of the contract as well as aggregated over the entire time horizon. The results show that Machine Learning can be used efficiently within PD term structure modeling. The Deep Neural Networks outperform the Markov Chain model in all performance metrics, whereas the Gradient Boosted Trees are better in all except one metric. For short-term predictions, the Machine Learning models barely outperform the Markov Chain model. For long-term predictions, however, the Machine Learning models are superior. / Flertalet s.k. Köp nu, betala senare-företag har växt fram under de senaste åren. En sorts finansiell institution som erbjuder kortsiktiga konsumentkreditskontrakt. I samband med att dessa företag har blivit alltmer populära, har deras åtagna kreditrisk ökat drastiskt. Samtidigt måste de regulatoriska kraven ställda av IFRS 9 efterlevas. Specifikt måste fallisemangsrisken för hela livslängden av ett sådant kontrakt estimeras. Samlingen av inkrementell fallisemangsrisk under hela kontraktets förlopp kallas fallisemangsriskens terminsstruktur. Precisa estimat av fallisemangsriskens terminsstruktur är önskvärda eftersom de understödjer verksamhetsbeslut baserat på en given riskaptit, samtidigt som de nuvarande regulatoriska kraven efterlevs. I denna uppsats undersöks effektiviteten av Maskininlärning för modellering av fallisemangsriskens terminsstruktur. Två kategorier av Maskinlärningsalgoritmer, i fem variationer vardera, utvärderas; (1) Djupa neuronnät; och (2) Gradient boosted trees. Maskininlärningsmodellerna jämförs mot en traditionell Markovkedjemodell. Modellernas prestanda mäts via en uppsättning kalibrerings- och diskrimineringsmått, utvärderade i varje tidssteg av kontraktet samt aggregerade över hela tidshorisonten. Resultaten visar att Maskininlärning är effektivt för modellering av fallisemangsriskens terminsstruktur. De djupa neuronnäten överträffar Markovkedjemodellen i samtliga prestandamått, medan Gradient boosted trees är bättre i alla utom ett mått. För kortsiktiga prediktioner är Maskininlärningsmodellerna knappt bättre än Markovkedjemodellen. För långsiktiga prediktioner, däremot, är Maskininlärningsmodellerna överlägsna.

No description available.

No description available.

Krebs ist die zweithäufigste Todesursache weltweit und zählt damit zu den größten Plagen der Menschheit. Jährlich sterben Menschen an den Folgen bösartiger Tumore und stellen Ärzte vor scheinbar unlösbare Aufgaben. Um Krebsgeschwüre effizient bekämpfen oder sogar vollständig beseitigen zu können, ist es enorm wichtig diese früh genug zu diagnostizieren. Oft stellt jedoch genau das in der Praxis ein großes Problem dar und Tumore werden erst dann als solche erkannt, wenn das Zellwachstum schon sehr weit fortgeschritten ist. Eine große Chance für die frühzeitige Erkennung von Krebs bieten unterdessen Deep Learning Algorithmen. Die vorliegende Seminararbeit stellt diese Verfahren und ihre Anwendung in der Krebsdiagnostik vor. Es wird hierbei genauer auf Convolutional Neural Networks eingegangen, die besonders gut geeignet für die Analyse von Gewebebildern sind und unter anderem auch im System von Google's DeepMind zum Einsatz kommen. Die Arbeit analysiert Chancen und Risiken des Einsatzes von Deep Neural Networks bei der Diagnose von bösartigen Tumoren und verschafft dem Leser damit einen ganzheitlichen Überblick über die Anwendung von Deep Neural Networks im Bereich der Onkologie.:1 Einleitung 2 Vom Neuronalen Netz zum Deep Learning Algorithmus 2.1 Grundlagen Künstlicher Neuronaler Netze 2.1.1 Allgemeiner Aufbau 2.1.2 Das Neuron als Grundbaustein 2.1.3 Lernen in neuronalen Netzen 2.1.4 Loss Function und Optimizer 2.2 Convolutional Neural Networks 2.2.1 Convolutional Layer 2.2.2 Pooling Layer 2.2.3 Fully Connected Layer 2.2.4 Lernen und Aktivierung in CNN’s 3 DeepMind als Deep Learning Multitalent 3.1 Bisherige Erfolge 3.2 DeepMind Health 4 Chancen und Risiken in der Krebsdiagnostik 4.1 Aktueller Stand der Brustkrebsdiagnostik 4.2 Chancen von Deep Learning Algorithmen 4.3 Ethische Risiken 4.3.1 False Positives 4.3.2 False Negatives 4.4 Fazit der Risikoanalyse 5 Ausblick