Slay the Spire is a complex deck-building and roguelike game with many possibilities of improving players ability to win. An important part of Slay the Spire is choosing a path that makes the players character as successful as possible. In this study we show that machine learning can help players pick better paths by creating an Artificial Neural Network (ANN) that predicts the most successful path of all available paths, we also discuss what makes a path successful. This study performed two experiments, one user study and one simulation experiment, with the intention of evaluating the created ANN and analysing what makes paths successful. Through the user study this paper shows that the ANN was effective at predicting paths, outperforming all other human players who played normally in all three cases. This study concludes that machine learning can be used effectively to help make pathing decisions in Slay the Spire. Furthermore the study proves the importance of the room types ’Elite’ and ’Campfires’ through the simulation experiment, user study and analysis of data from previous playthroughs.

Human key point tracking such as face detection and recognition has become an increasingly popular research topic. It is a platform independent functionality and already being implemented on a wide range of platforms. Android is one such platform that runs on mobile phones and top of many edge devices such as car devices and smart home appliances. In the current times, AI and ML related applications are slightly moving into those edge devices due to various reasons such as security and low latency. The hardware enhancements are also backing this trend that happened over the last few years. Many solutions and algorithms have been proposed in this context, and various frameworks and models have also been developed. Even though there are different models available, they tend to deliver varying results in terms of performance. Evaluating these different alternatives to find an optimized solution is a problem worth addressing. In this thesis project, several selected face detection and recognition models have been implemented in an Android device, and their performance been evaluated. Google ML Kit showed the best results among the face detection methods since it took only around 68 milliseconds on average to detect a face. Out of the three face recognition algorithms evaluated, FaceNet was the most accurate as it showed an accuracy above 95% for most cases. Meanwhile, MobileFaceNet was the fastest algorithm, and it took only around 90 milliseconds on average to produce and output. Eventually, a face recognition application was also developed using the best performing models selected from the experiment.

Today's smartphones are capable of accomplishing far more advanced tasks than reading emails. With the modern framework TensorFlow, visual object recognition becomes possible using smartphone resources. This thesis shows that the main challenge does not lie in developing an artifact which performs visual object recognition. Instead, the main challenge lies in developing an ecosystem which allows for continuous improvement of the system’s ability to accomplish the given task without laborious and inefficient data collection. This thesis presents four design principles which contribute to an efficient ecosystem with quick initiation of new object classes and efficient data collection which is used to continuously improve the system’s ability to recognize smart meters in varying environments in an automated fashion.

Syftet med studien är att jämföra tre deep learning nätverk med varandra för att ta reda på vilket nätverk som kan producera den högsta uppmätta noggrannheten. Noggrannheten mäts genom att nätverken försöker förutspå antalet personer som vistas i rummet där observation äger rum. Utöver att jämföra de tre djupinlärningsnätverk med varandra, kommer vi även att jämföra dem med en traditionell metoder inom maskininlärning - i syfte för att ta reda på ifall djupinlärningsnätverken presterar bättre än vad traditionella metoder gör. I studien används design and creation. Design and creation är en forskningsmetodologi som lägger stor fokus på att utveckla en IT produkt och använda produkten som dess bidrag till ny kunskap. Metodologin har fem olika faser, vi valde att göra en iterativ process mellan utveckling- och utvärderingfaserna. Observation är den datagenereringsmetod som används i studien för att samla in data. Datagenereringen pågick under tre veckor och under tiden hann 31287 rader data registreras i vår databas. Ett av våra nätverk fick vi en noggrannhet på 78.2%, de andra två nätverken fick en noggrannhet på 45.6% respektive 40.3%. För våra traditionella metoder använde vi ett beslutsträd med två olika formler, de producerade en noggrannhet på 61.3% respektive 57.2%. Resultatet av denna studie visar på att utav de tre djupinlärningsnätverken kan endast en av djupinlärningsnätverken producera en högre noggrannhet än de traditionella maskininlärningsmetoderna. Detta resultatet betyder nödvändigtvis inte att djupinlärningsnätverk i allmänhet kan producera en högre noggrannhet än traditionella maskininlärningsmetoder. Ytterligare arbete som kan göras är följande: ytterligare experiment med datasetet och hyperparameter av djupinlärningsnätverken, samla in mer data och korrekt validera denna data och jämföra fler djupinlärningsnätverk och maskininlärningsmetoder. / The purpose of the study is to compare three deep learning networks with each other to evaluate which network can produce the highest prediction accuracy. Accuracy is measured as the networks try to predict the number of people in the room where observation takes place. In addition to comparing the three deep learning networks with each other, we also compare the networks with a traditional machine learning approach - in order to find out if deep learning methods perform better than traditional methods do. This study uses design and creation. Design and creation is a methodology that places great emphasis on developing an IT product and uses the product as its contribution to new knowledge. The methodology has five different phases; we choose to make an iterative process between the development and evaluation phases. Observation is the data generation method used to collect data. Data generation lasted for three weeks, resulting in 31287 rows of data recorded in our database. One of our deep learning networks produced an accuracy of 78.2% meanwhile, the two other approaches produced an accuracy of 45.6% and 40.3% respectively. For our traditional method decision trees were used, we used two different formulas and they produced an accuracy of 61.3% and 57.2% respectively. The result of this thesis shows that out of the three deep learning networks included in this study, only one deep learning network is able to produce a higher predictive accuracy than the traditional ML approaches. This result does not necessarily mean that deep learning approaches in general, are able to produce a higher predictive accuracy than traditional machine learning approaches. Further work that can be made is the following: further experimentation with the dataset and hyperparameters, gather more data and properly validate this data and compare more and other deep learning and machine learning approaches.

This paper concerns itself with object detection as a possible solution to Valmet’s quest for a visual-feedback system that can help operators and other personnel to more easily interact with their machines and equipment. New advancements in deep learning, specifically CNN models, have been exploring neural networks with detection-capabilities. Object detection has historically been mostly inaccessible to the industry due the complex solutions involving various tricky image processing algorithms. In that regard, deep learning offers a more easily accessible way to create scalable object detection solutions. This study has therefore chosen to review recent literature detailing detection models with a selective focus on factors making them realizable on ARM hardware and in turn mobile devices like phones. An attempt was made to single out the most lightweight and hardware efficient model and implement it as a prototype in order to help Valmet in their decision process around future object detection products. The survey led to the choice of a SSD-MobileNetsV2 detection architecture due to promising characteristics making it suitable for performance-constrained smartphones. This CNN model was implemented on Valmet’s phone of choice, Samsung Galaxy S8, and it successfully achieved object detection functionality. Evaluation shows a mean average precision of 60 % in detecting objects and a 4.7 FPS performance on the chosen phone model. TensorFlow was used for developing, training and evaluating the model. The report concludes with recommending Valmet to pursue solutions built on-top of these kinds of models and further wishes to express an optimistic outlook on this type of technology for the future. Realizing performance of this magnitude on a mid-tier phone using deep learning (which historically is very computationally intensive) sets us up for great strides with this type of technology in the future; and along with better smartphones, great benefits are expected to both industry and consumers. / Den här rapporten behandlar objekt detektering som en möjlig lösning på Valmets efterfrågan av ett visuellt återkopplingssystem som kan hjälpa operatörer och annan personal att lättare interagera med maskiner och utrustning. Nya framsteg inom djupinlärning har dem senaste åren möjliggjort framtagande av neurala nätverksarkitekturer med detekteringsförmågor. Då industrisektorn svårare tar till sig högst specialiserade algoritmer och komplexa bildbehandlingsmetoder (som tidigare varit fallet med objekt detektering) så ger djupinlärningsmetoder istället upphov till att skapa självlärande system som är återanpassningsbara och närmast intuitiva i dem fall där sådan teknologi åberopas. Den här studien har därför valt att studera ett par sådana teknologier för att hitta möjliga implementeringar som kan realiseras på något så enkelt som en mobiltelefon. Urvalet har därför bestått i att hitta detekteringsmodeller som är hårdvarumässigt resurssnåla och implementera ett sådant system för att agera prototyp och underlag till Valmets vidare diskussioner kring objekt-detekteringsslösningar. Studien valde att implementera en SSD-MobileNetsV2 modellarkitektur då den uppvisade lovande egenskaper kring hårdvarukraven. Modellen implementerades och utvärderades på Valmets mest förekommande telefon Samsung Galaxy S8 och resultatet visade på en god förmåga för modellen att detektera objekt. Den valda modellen gav 60 % precision på utvärderingsbilderna och lyckades nå 4.7 FPS på den implementerade telefonen. TensorFlow användes för programmering och som stödjande mjukvaruverktyg för träning, utvärdering samt vidare implementering. Studien påpekar optimistiska förväntningar av denna typ av teknologi; kombinerat med bättre smarttelefoner i framtiden kan det leda till revolutionerande lösningar för både industri och konsumenter.

<div>The recent advances in articial neural networks have demonstrated competitive performance of deep neural networks (and it is comparable with humans) on tasks like image classication, natural language processing and time series classication. These large scale networks pose an enormous computational challenge, especially in resource constrained devices. The current work proposes a targeted-rank based framework for accelerated computation of wide neural networks. It investigates the problem of rank-selection for tensor ring nets to achieve optimal network compression. When applied to a state of the art wide residual network, namely WideResnet, the framework yielded a signicant reduction in computational time. The optimally compressed non-parallel WideResnet is faster to compute on a CPU by almost 2x with only 5% degradation in accuracy when compared to a non-parallel implementation of uncompressed WideResnet.</div>

The use of machine learning and specifically neural networks is a growing trend in software development, and has grown immensely in the last couple of years in the light of an increasing need to handle big data and large information flows. Machine learning has a broad area of application, such as human-computer interaction, predicting stock prices, real-time translation, and self driving vehicles. Large companies such as Microsoft and Google have already implemented machine learning in some of their commercial products such as their search engines, and their intelligent personal assistants Cortana and Google Assistant. The main goal of this project was to evaluate the two deep learning frameworks Google TensorFlow and Microsoft CNTK, primarily based on their performance in the training time of neural networks. We chose to use the third-party API Keras instead of TensorFlow's own API when working with TensorFlow. CNTK was found to perform better in regards of training time compared to TensorFlow with Keras as frontend. Even though CNTK performed better on the benchmarking tests, we found Keras with TensorFlow as backend to be much easier and more intuitive to work with. In addition, CNTKs underlying implementation of the machine learning algorithms and functions differ from that of the literature and of other frameworks. Therefore, if we had to choose a framework to continue working in, we would choose Keras with TensorFlow as backend, even though the performance is less compared to CNTK.

本研究主旨是希望提供一個智能金融演算法交易平台，以Django CMS作為網頁框架，區分成研發環境與交易環境，完整的功能包含用戶研發、用戶測試以及使用演算法服務。用戶研發與測試上採用IPython的互動式開發介面，利用JupyterHub進行管理與配置，能夠同時提供多個用戶存取平台，使得平台足以負載大規模用戶的使用；而演算法服務經由Celery包裝成任務，以利交付給後台進行分散式運算。搭上近年來深度學習的熱潮，平台額外擴充Tensorflow套件與GPU建置，支援多核及高速演算法運算。 面對存取大量、複雜且結構化的金融資料，本研究的資料庫採用HAWQ做為解決方案，利用其極大量平行化的架構，改善過往存取大數據所造成的系統複雜性與效能瓶頸，並搭配Ambari達到創建、監視及管理Hadoop分散式集群的功用，讓開發者在部署與維運上都將事半功倍。 由於採用新的資料庫HAWQ，傳統的資料表設計將不利反傷，因此本研究會針對程式端存取資料庫裡的金融資料，量身打造適合的資料表設計，並對其做效能評測，以確保資料能有效且迅速地被程式所取用。 / The purpose of this research is to provide a smartly algorithmic trading platform with financial data. I use Django CMS as a web framework and consisting of Develop environment and Trade environment. The entire functions of the platform include “User Research and Development”,” User Testing” and “Algorithmic Services”. “User Research and Development” and “User Testing” using IPython interactive development interface, with JupyterHub management and configuration, can simultaneously provide multiple user accessing and make the platform enough to support more and more users; “Algorithmic Services” using Celery to package algorithms into tasks can facilitate the delivery to the Server for distributed computing. By means of the growth of Deep Learning in recent years, the platform adds extra Tensorflow and GPU deployment to support multi-core and high-speed algorithm computing. In face of accessing large number of complex and structured financial data, I choose HAWQ as the database in this research. Its extremely massively parallel processing can alleviate the complexity of system and the bottlenecks of efficiency caused by accessing massive number of data. Combing HAWQ with Ambari can achieve the functions of creation, monitoring and management of Hadoop distributed cluster. The developers will do much more easily in deployment and maintenance. The traditional table design may not fit in with the new database HAWQ, so this research will design appropriate table, and evaluate its performance to ensure that data can be accessed effectively and quickly from programs.

This master‘s thesis deals with the Deep Learning methods for image recognition tasks from the first methods to the modern ones. The main focus is on convolutional neural nets based models for classification, detection and image segmentation. These methods are used for practical implemetation – counting passing cars on video from traffic camera. After several test of available models, the YOLOv2 architecture was chosen and retrained on own dataset. The application also includes the addition of the SORT tracking algorithm.

This paper introduces Bayesian neural network based on Occams razor. Basic knowledge about neural networks and Bayes rule is summarized in the first part of this paper. Principles of Occams razor and Bayesian neural network are explained. A real case of use is introduced (about predicting landslide). The second part of this paper introduces how to construct Bayesian neural network in Python. Such an application is shown. Typical behaviour of Bayesian neural networks is demonstrated using example data.