The stock market is a non-linear field, but many of the best-known portfolio optimization algorithms are based on linear models. In recent years, the rapid development of machine learning has produced flexible models capable of complex pattern recognition. In this paper, we propose two different methods of portfolio optimization; one based on the development of a multivariate time-dependent neural network,thelongshort-termmemory(LSTM),capable of finding lon gshort-term price trends. The other is the linear Markowitz model, where we add an exponential moving average to the input price data to capture underlying trends. The input data to our neural network are daily prices, volumes and market indicators such as the volatility index (VIX).The output variables are the prices predicted for each asset the following day, which are then further processed to produce metrics such as expected returns, volatilities and prediction error to design a portfolio allocation that optimizes a custom utility function like the Sharpe Ratio. The LSTM model produced a portfolio with a return and risk that was close to the actual market conditions for the date in question, but with a high error value, indicating that our LSTM model is insufficient as a sole forecasting tool. However,the ability to predict upward and downward trends was somewhat better than expected and therefore we conclude that multiple neural network can be used as indicators, each responsible for some specific aspect of what is to be analysed, to draw a conclusion from the result. The findings also suggest that the input data should be more thoroughly considered, as the prediction accuracy is enhanced by the choice of variables and the external information used for training. / Aktiemarknaden är en icke-linjär marknad, men många av de mest kända portföljoptimerings algoritmerna är baserad på linjära modeller. Under de senaste åren har den snabba utvecklingen inom maskininlärning skapat flexibla modeller som kan extrahera information ur komplexa mönster. I det här examensarbetet föreslår vi två sätt att optimera en portfölj, ett där ett neuralt nätverk utvecklas med avseende på multivariata tidsserier och ett annat där vi använder den linjära Markowitz modellen, där vi även lägger ett exponentiellt rörligt medelvärde på prisdatan. Ingångsdatan till vårt neurala nätverk är de dagliga slutpriserna, volymerna och marknadsindikatorer som t.ex. volatilitetsindexet VIX. Utgångsvariablerna kommer vara de predikterade priserna för nästa dag, som sedan bearbetas ytterligare för att producera mätvärden såsom förväntad avkastning, volatilitet och Sharpe ratio. LSTM-modellen producerar en portfölj med avkastning och risk som ligger närmre de verkliga marknadsförhållandena, men däremot gav resultatet ett högt felvärde och det visar att vår LSTM-modell är otillräckligt för att använda som ensamt predikteringssverktyg. Med det sagt så gav det ändå en bättre prediktion när det gäller trender än vad vi antog den skulle göra. Vår slutsats är därför att man bör använda flera neurala nätverk som indikatorer, där var och en är ansvarig för någon specifikt aspekt man vill analysera, och baserat på dessa dra en slutsats. Vårt resultat tyder också på att inmatningsdatan bör övervägas mera noggrant, eftersom predikteringsnoggrannheten.

The low amount solved residential burglary crimes calls for new and innovative methods in the prevention and investigation of the cases. There were 22 600 reported residential burglaries in Sweden 2017 but only four to five percent of these will ever be solved. There are many initiatives in both Sweden and abroad for decreasing the amount of occurring residential burglaries and one of the areas that are being tested is the use of prediction methods for more efficient preventive actions. This thesis is an investigation of a potential method of prediction by using neural networks to identify areas that have a higher risk of burglaries on a daily basis. The model use reported burglaries to learn patterns in both space and time. The rationale for the existence of patterns is based on near repeat theories in criminology which states that after a burglary both the burgled victim and an area around that victim has an increased risk of additional burglaries. The work has been conducted in cooperation with the Swedish Police authority. The machine learning is implemented with convolutional long short-term memory (LSTM) neural networks with max pooling in three dimensions that learn from ten years of residential burglary data (2007-2016) in a study area in Stockholm, Sweden. The model's accuracy is measured by performing predictions of burglaries during 2017 on a daily basis. It classifies cells in a 36x36 grid with 600 meter square grid cells as areas with elevated risk or not. By classifying 4% of all grid cells during the year as risk areas, 43% of all burglaries are correctly predicted. The performance of the model could potentially be improved by further configuration of the parameters of the neural network, along with a use of more data with factors that are correlated to burglaries, for instance weather. Consequently, further work in these areas could increase the accuracy. The conclusion is that neural networks or machine learning in general could be a powerful and innovative tool for the Swedish Police authority to predict and moreover prevent certain crime. This thesis serves as a first prototype of how such a system could be implemented and used.

Hierarchical clustering is a family of machine learning methods that has many applications, amongst other data science and data mining. This thesis belongs to the research area of brain-like computing and introduces a novel approach to hierarchical clustering using a brain-like recurrent neural network. Attractor networks can cluster samples by converging to the same network state. We modulate the network behaviour by varying a parameter in the activity propagation rule such that the granularity of the resulting clustering is changed. A hierarchical clustering is then created by combining multiple levels of granularity. The method is developed for two different datasets and evaluated on a variety of clustering metrics. Its performance is compared to standard clustering algorithms and the structure and composition of the clustering is inspected. We show that the method can produce clusterings for different levels of granularity and new data without retraining. As a novel clustering method, it is relevant to machine learning applications. As a model for hierarchical recall in a memory model, it is relevant to computational neuroscience and neuromorphic computing. / Hierarkiskt klusterarbete är en grupp av maskininlärningsmetoder som har många tillämpningar, bland annat datavetenskap och datagrävning. Denna avhandling tillhör forskningsområdet för hjärnlikt databehandling och introducerar ett nytt tillvägagångssätt för hierarkiskt klusterarbete med hjälp av ett hjärnlikt återkommande neuronnätverk. Attraktornätverk kan klustra prover genom att konvergera till samma nätverksstadium. Vi modulerar nätverkets beteende genom att variera en parameter i regeln för aktivitetspropagering så att granulariteten i det resulterande klusterarbetet förändras. Ett hierarkiskt klusterarbete skapas sedan genom att kombinera flera nivåer av granularitet. Metoden utvecklas för två olika datasets och utvärderas med hjälp av olika klustringsmått. Dess prestanda jämförs med standard klusteringsalgoritmer och strukturen och sammansättningen av klusterarbetet inspekteras. Vi visar att metoden kan producera klusterarbeten för olika nivåer av granularitet och nya data utan omträning. Som en ny klusteringsmetod är den relevant för maskininlärningsapplikationer. Som en modell för hierarkisk återkallelse i en minnesmodell är den relevant för beräkningsneurovetenskap och neuromorfisk databehandling.

For music genre classification purposes, the importance of an intelligent and content-based selection of audio samples has been mostly overlooked. One common approach toward representative results is to select samples at predetermined locations. This is done to avoid analysis of the full audio during classification. While methods in music thumbnailing could be used to find representative samples for genre classification, it has not yet been demonstrated. This thesis showed that efficient and genre representative sampling can be performed with a machine learning model (bidirectional RNN with either LSTM or GRU cells). The model was trained using a sub-optimal genre classifier and computationally inexpensive audio features. The genre classifier was used to compute losses for evenly spaced samples in 14000 tracks. The losses were then used as targets during training. Root mean square energy and zero-crossing rate were used as features, computed over relatively large time steps and wide intervals. The proposed framework can be used to give better predictions with trained genre classifiers and most likely also train, or retrain, them for higher classification accuracy at a low computational cost. / Vid musikgenreklassificering har betydelsen av ett intelligent och innehållsbaserat urval allt som oftast förbisetts. En ansats till ett representativt resultat görs vanligtvis genom att ett antal kortare utdrag tas vid förutbestämda tidpunkter. Detta görs för att under en klassificering undvika att analysera hela musikverket. Fastän det existerar metoder inom music thumbnailing för att hitta representativa urval har de ännu inte tillämpats inom genreklassificering. I denna uppsats visades att ett effektivt och genrerepresentativt musikurval kan utföras med en maskininlärningsmodell (dubbelriktad RNN med antingen LSTM- eller GRU-celler). Modellen tränades med hjälp av en suboptimal genreklassificerare och beräkningsmässigt enkla ljudattribut. Genreklassificeraren användes för att beräkna förlusten av jämnt fördelade urval i 14000 musikverk. Förlusterna användes sedan som utdata under träningen. Kvadratiskt energimedelvärde och zero-crossing rate beräknades över relativt långa tidssteg och breda intervall och användes som indata. Det föreslagna ramverket kan till beräkningsmässigt låga kostnader användas för att ge bättre förutsägelser med redan tränade genreklassificerare och sannolikt träna, eller omträna, dessa för högre noggrannhet vid klassificering.

The aim of this paper is first of all to determine whether deep learning methods can recover trading strategies based on historical price and volume data, with scarcity of real data in mind. The second aim is to evaluate the methods to generate a deep learning blueprint for strategy extraction. Trading strategies can be built on many different types of data, often combined from different areas. In this paper, we focus on trading strategies based solely on historical price and volume data to limit the scope of the problem. Combinations of different deep learning architectures and methods such as transfer- and ensemble methods were evaluated. The results clearly show that deep learning models can recover relatively complex trading strategies to some extent. Models leveraging transfer learning outperform other models when data is scarce and ensemble methods elevate performance in certain regards. / Målet med denna rapport är i första hand att ta reda på om djupinlärningsmetoder kan återskapa handlingsstragetier baserat på historiska priser och volymdata, med vetskapen att datan är begränsad. Det andra målet är att utvärdera metoder för att skapa en djupinlärningsmall för att utvinna handelsstrategier. Handelsstrategier kan vara byggda på många olika datatyper, ofta i kombination från olika områden. I denna rapport fokuserar vi på strategier som enbart är baserade på historiska priser och volymdata för att begränsa problemet. Kombinationer av olika djupinlärningsarkitekturer tillsammans med metoder som till exempel överföringsinlärning och ensembleinlärning utvärderades. Resultaten visar tydligt att djupinlärningsmodeller kan återskapa relativt komplexa handlingsstrategier. Modeller som utnyttjade överföringsinlärning presterade bättre än andra modeller när datan var begränsad och ensembleinlärning ökade prestandan ytterligare i vissa sammanhang. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

The growing demand for sustainable technology has led to an increased application of power electronics. As these devices are often exposed to harsh conditions, their reliability is a primary concern for both manufacturers and users. Addressing these reliability challenges involves a set of activities known as Prognostics and Health Management (PHM). In PHM, predicting the Remaining Useful Life (RUL) is crucial. This prediction relies on identifying failure precursors, which signify the presence of degradation. These precursors are then used to construct a degradation model that enables the prediction of the remaining time that the device can work before failure. The project focuses on examining a MOSFET aging dataset from the NASA PCoE dataset depository and a diode aging dataset from Fraunhofer ENAS. The prediction of the remaining useful life of devices using failure precursors has been done by applying recurrent neural network (RNN) methods. However, the prediction results from a single feature is significantly deviated from the actual values. To improve the prediction, the age of the device was proposed as an additional feature. RNNs with a similar number of weights and RNNs with the same hyperparameters are implemented and their performance is evaluated by the accuracy of prediction. The results show that all the RNN models implemented manage to capture the characteristics of the aging data. Despite its simpler structure, the vanilla RNN manages to produce a comparable result with the GRU and LSTM by simpler mechanism and less number of weights. The results also reveal that the characteristics of the data have a significant impact on the final results. / Den växande efterfrågan på hållbar teknik har lett till en ökad tillämpning av kraftelektronik. Eftersom dessa enheter ofta utsätts för tuffa förhållanden är deras tillförlitlighet ett primärt bekymmer för både tillverkare och användare. Att ta itu med dessa tillförlitlighetsutmaningar innebär en uppsättning aktiviteter som kallas Prognostics and Health Management (PHM). I PHM är det avgörande att förutsäga det återstående användbara livet (RUL). Denna förutsägelse bygger på identifiering av felprekursorer, som anger förekomsten av nedbrytning. Dessa prekursorer används sedan för att konstruera en nedbrytningsmodell som möjliggör förutsägelse av den återstående tiden som enheten kan fungera innan fel. Projektet fokuserar på att undersöka en MOSFET-åldringsdataset från NASA PCoE-datauppsättningen och en diodåldringsdataset från Fraunhofer ENAS. Förutsägelsen av den återstående livslängden för enheter som använder felprekursorer har gjorts genom att använda metoder för återkommande neurala nätverk (RNN). Förutsägelseresultatet från en enskild funktion avviker dock avsevärt från de faktiska värdena. För att förbättra förutsägelsen föreslogs enhetens ålder som en extra funktion. RNN med ett liknande antal vikter och RNN med samma hyperparametrar implementeras och deras prestanda utvärderas av förutsägelsens noggrannhet. Resultaten visar att alla implementerade RNN-modeller lyckas fånga egenskaperna hos åldrande data. Trots sin enklare struktur lyckas vanilj RNN producera ett jämförbart resultat med GRU och LSTM genom enklare mekanism och färre antal vikter. Resultaten visar också att uppgifternas egenskaper har en betydande inverkan på de slutliga resultaten.

No description available.

No description available.

The hypothesis that similar chemicals exert similar biological activities has been widely adopted in the field of drug discovery and development. Quantitative Structure-Activity Relationship (QSAR) models have been used ubiquitously in drug discovery to understand the function of chemicals in biological systems. A common QSAR modeling method calculates similarity scores between chemicals to assess their biological function. However, due to the fact that some chemicals can be similar and yet have different biological activities, or conversely can be structurally different yet have similar biological functions, various methods have instead been developed to quantify chemical similarity at the functional level. Quantmap is one such method, which utilizes biological databases to quantify the biological similarity between chemicals. Quantmap uses quantitative molecular network topology analysis to cluster chemical substances based on their bioactivities. This method by itself, unfortunately, cannot assign new chemicals (those which may not yet have biological data) to the derived clusters. Owing to the fact that there is a lack of biological data for many chemicals, deep learning models were explored in this project with respect to their ability to correctly assign unknown chemicals to Quantmap clusters. The deep learning methods explored included both convolutional and recurrent neural networks. Transfer learning/pretraining based approaches and data augmentation methods were also investigated. The best performing model, among those considered, was the Seq2seq model (a recurrent neural network containing two joint networks, a perceiver and an interpreter network) without pretraining, but including data augmentation.

<p>The numerical simulation of physical systems plays a key role in different fields of science and engineering. The popularity of numerical methods stems from their ability to simulate complex physical phenomena for which analytical solutions are only possible for limited combinations of geometry, boundary, and initial conditions. Despite their flexibility, the computational demand of classical numerical methods quickly escalates as the size and complexity of the model increase. To address this limitation, and motivated by the unprecedented success of Deep Learning (DL) in computer vision, researchers started exploring the possibility of developing computationally efficient DL-based algorithms to simulate the response of complex systems. To date, DL techniques have been shown to be effective in simulating certain physical systems. However, their practical application faces an important common constraint: trained DL models are limited to a predefined set of configurations. Any change to the system configuration (e.g., changes to the domain size or boundary conditions) entails updating the underlying architecture and retraining the model. It follows that existing DL-based simulation approaches lack the flexibility offered by classical numerical methods. An important constraint that severely hinders the widespread application of these approaches to the simulation of physical systems.</p> <p><br></p> <p>In an effort to address this limitation, this dissertation explores DL models capable of combining the conceptual flexibility typical of a numerical approach for structural analysis, the finite element method, with the remarkable computational efficiency of trained neural networks. Specifically, this dissertation introduces the novel concept of <em>“Finite Element Network Analysis”</em> (FENA), a physics-informed, DL-based computational framework for the simulation of physical systems. FENA leverages the unique transfer knowledge property of bidirectional recurrent neural networks to provide a uniquely powerful and flexible computing platform. In FENA, each class of physical systems (for example, structural elements such as beams and plates) is represented by a set of surrogate DL-based models. All classes of surrogate models are pre-trained and available in a library, analogous to the finite element method, alleviating the need for repeated retraining. Another remarkable characteristic of FENA is the ability to simulate assemblies built by combining pre-trained networks that serve as surrogate models of different components of physical systems, a functionality that is key to modeling multicomponent physical systems. The ability to assemble pre-trained network models, dubbed <em>network concatenation</em>, places FENA in a new category of DL-based computational platforms because, unlike existing DL-based techniques, FENA does not require <em>ad hoc</em> training for problem-specific conditions.</p> <p><br></p> <p>While FENA is highly general in nature, this work focuses primarily on the development of linear and nonlinear static simulation capabilities of a variety of fundamental structural elements as a benchmark to demonstrate FENA's capabilities. Specifically, FENA is applied to linear elastic rods, slender beams, and thin plates. Then, the concept of concatenation is utilized to simulate multicomponent structures composed of beams and plate assemblies (stiffened panels). The capacity of FENA to model nonlinear systems is also shown by further applying it to nonlinear problems consisting in the simulation of geometrically nonlinear elastic beams and plastic deformation of aluminum beams, an extension that became possible thanks to the flexibility of FENA and the intrinsic nonlinearity of neural networks. The application of FENA to time-transient simulations is also presented, providing the foundation for linear time-transient simulations of homogeneous and inhomogeneous systems. Specifically, the concepts of Super Finite Network Element (SFNE) and network concatenation in time are introduced. The proposed concepts enable training SFNEs based on data available in a limited time frame and then using the trained SFNEs to simulate the system evolution beyond the initial time window characteristic of the training dataset. To showcase the effectiveness and versatility of the introduced concepts, they are applied to the transient simulation of homogeneous rods and inhomogeneous beams. In each case, the framework is validated by direct comparison against the solutions available from analytical methods or traditional finite element analysis. Results indicate that FENA can provide highly accurate solutions, with relative errors below 2 % for the cases presented in this work and a clear computational advantage over traditional numerical solution methods. </p> <p><br></p> <p>The consistency of the performance across diverse problem settings substantiates the adaptability and versatility of FENA. It is expected that, although the framework is illustrated and numerically validated only for selected classes of structures, the framework could potentially be extended to a broad spectrum of structural and multiphysics applications relevant to computational science.</p>