In the ever-changing landscape of the fishing industry, demands for automating specific processes are increasing substantially. Predicting future events eliminates much of the existing communication latency between fishing vessels and their customers and makes real-time analysis of onboard catch possible for the fishing industry. Further, machine learning models, may reduce the number of human resources necessary for the numerous processes that may be automated. In this document, we focus on weight estimation of three different species of fish. Namely, we want to estimate the fish weight given its specie through datadriven techniques. Due to the high complexity of image data, the overhead expenses of collecting images at sea, and the complexities of fish features, we consider a dimensionality reduction on the inputs to reduce the curse of dimensionality and increase interpretability. We will study the viability of modeling fish weights from lower-dimensional feature vectors and the conjunction of lower-dimensional feature vectors and algorithmically obtained features. We found that modeling the residuals with latent representations of a simple power model fitted on length features resulted in a significant difference in the weight estimates for two types of fish and a decrease in Root Mean Squared Error (rMSE) and Mean Absolute Percentage Error (MAPE) scores in favour of the estimations utilizing latent representations. / I fiskeindustrins ständigt föränderliga landskap ökar kraven på att automatisera specifika processer väsentligt. Att förutsäga framtida händelser eliminerar mycket av den befintliga kommunikationsfördröjningen mellan fiskefartyg och deras kunder och möjliggör analys i realtid av ombordfångst för fiskeindustrin. Vidare kan det minska antalet personalresurser som krävs för de många processer som kan automatiseras. I detta dokument studerar vi två olika beslutsproblem relaterade till att sortera fisk av tre olika arter. Vi vill nämligen bestämma fiskvikten och dess art genom datadrivna tekniker. På grund av bilddatas höga komplexitet, de allmänna kostnaderna för att samla bilder till sjöss och komplexiteten hos fiskegenskaper, anser vi att en dimensionalitetsminskning av särdragen minskar problemet relaterat till dimensionsexplosion och ökar tolkbarheten. Vi kommer att studera lämpligheten av modellering av fiskvikter och arter från lägre dimensionella särdragsvektorer samt kombinationen av dessa med algoritmiskt erhållna funktioner. Vi fann att modellering av residual med latenta representationer av en enkel potensfunktionsmodell som är anpassad till fisklängder resulterade i en signifikant skillnad i viktuppskattningarna för två typer av fisk och en minskning av rMSE och MAPE poäng.

The Natural Language Processing (NLP) research area has seen notable advancements in recent years, one being the ELECTRA model which improves the sample efficiency of BERT pre-training by introducing a discriminative pre-training approach. Most publicly available language models are trained on general-domain datasets. Thus, research is lacking for niche domains with domain-specific vocabulary. In this paper, the process of adapting a BERT-like model to the telecom domain is investigated. For efficiency in training the model, the ELECTRA approach is selected. For measuring target- domain performance, the Question Answering (QA) downstream task within the telecom domain is used. Three domain adaption approaches are considered: (1) continued pre- training on telecom-domain text starting from a general-domain checkpoint, (2) pre-training on telecom-domain text from scratch, and (3) pre-training from scratch on a combination of general-domain and telecom-domain text. Findings indicate that approach 1 is both inexpensive and effective, as target- domain performance increases are seen already after small amounts of training, while generalizability is retained. Approach 2 shows the highest performance on the target-domain QA task by a wide margin, albeit at the expense of generalizability. Approach 3 combines the benefits of the former two by achieving good performance on QA both in the general domain and the telecom domain. At the same time, it allows for a tokenization vocabulary well-suited for both domains. In conclusion, the suitability of a given domain adaption approach is shown to depend on the available data and computational budget. Results highlight the clear benefits of domain adaption, even when the QA task is learned through behavioral fine-tuning on a general-domain QA dataset due to insufficient amounts of labeled target-domain data being available. / Dubbelriktade språkmodeller som BERT har på senare år nått stora framgångar inom språkteknologiområdet. Flertalet vidareutvecklingar av BERT har tagits fram, bland andra ELECTRA, vars nyskapande diskriminativa träningsprocess förkortar träningstiden. Majoriteten av forskningen inom området utförs på data från den allmänna domänen. Med andra ord finns det utrymme för kunskapsbildning inom domäner med områdesspecifikt språk. I detta arbete utforskas metoder för att anpassa en dubbelriktad språkmodell till telekomdomänen. För att säkerställa hög effektivitet i förträningsstadiet används ELECTRA-modellen. Uppnådd prestanda i måldomänen mäts med hjälp av ett frågebesvaringsdataset för telekom-området. Tre metoder för domänanpassning undersöks: (1) fortsatt förträning på text från telekom-området av en modell förtränad på den allmänna domänen; (2) förträning från grunden på telekom-text; samt (3) förträning från grunden på en kombination av text från telekom-området och den allmänna domänen. Experimenten visar att metod 1 är både kostnadseffektiv och fördelaktig ur ett prestanda-perspektiv. Redan efter kort fortsatt förträning kan tydliga förbättringar inom frågebesvaring inom måldomänen urskiljas, samtidigt som generaliserbarhet kvarhålls. Tillvägagångssätt 2 uppvisar högst prestanda inom måldomänen, om än med markant sämre förmåga att generalisera. Metod 3 kombinerar fördelarna från de tidigare två metoderna genom hög prestanda dels inom måldomänen, dels inom den allmänna domänen. Samtidigt tillåter metoden användandet av ett tokenizer-vokabulär väl anpassat för båda domäner. Sammanfattningsvis bestäms en domänanpassningsmetods lämplighet av den respektive situationen och datan som tillhandahålls, samt de tillgängliga beräkningsresurserna. Resultaten påvisar de tydliga vinningar som domänanpassning kan ge upphov till, även då frågebesvaringsuppgiften lärs genom träning på ett dataset hämtat ur den allmänna domänen på grund av otillräckliga mängder frågebesvaringsdata inom måldomänen.

Today, there is a demand for reliable ways to perform automatic modulation recognition of Low Probability of Intercept (LPI) radar signals, not least in the defense industry. This study explores the possibility of performing automatic modulation recognition on these signals through clustering and more specifically how to learn representations of input signals for this task. A semi-supervised approach using a bootstrapped convolutional neural network classifier for representation learning is proposed. A comparison is made between training the representation learner on raw time-series and on spectral representations of the input signals. It is concluded that, overall, the system trained on spectral representations performs better, though both approaches show promise and should be explored further. The proposed system is tested both on known modulation types and on previously unseen modulation types in the task of novelty detection. The results show that the system can successfully identify known modulation types with adjusted mutual information of 0.86 for signal-to-noise ratios ranging from -10 dB to 10 dB. When introducing previously unseen modulations, up to six modulations can be identified with adjusted mutual information above 0.85. Furthermore, it is shown that the system can learn to separate LPI radar signals from telecom signals which are present in most signal environments. / Idag finns ett behov av pålitlig automatiserad modulationsigenkänning (AMR) av Low Probability of Inercept (LPI)-radarsignaler, inte minst hos försvarsindustrin. Denna studie utforskar möjligheten att utföra AMR av dessa signaler genom klustring och mer specifikt hur man bör lära in representationer av signalerna i detta syfte. En halvövervakad inlärningsmetod som använder en klassificerare baserad på faltningsnätverk föreslås. En jämförelse görs mellan ett system som tränar för representationsinlärning på råa tidsserier och ett system som tränar på spektrala representationer av signalerna. Resultaten visar att systemet tränat på spektrala representationer på det stora hela presterar bättre, men båda metoderna visar lovande resultat och bör utforskas vidare. Systemet testas på signaler från både kända och för systemet tidigare okända modulationer i syfte att pröva förmågan att upptäcka nya typer av modulationer. Systemet identifierar kända modulationer med adjusted mutual information på 0.86 i brusnivåer från -10 dB till 10 dB. När tidigare okända modulationer introduceras till systemet ligger adjusted mutual information över 0.85 för upp till sex modulationer. Studien visar dessutom att systemet kan lära sig skilja LPI-radarsignaler från telekommunikationssignaler som är vanliga i de flesta signalmiljöer.

In recent years, machine learning models have gained traction in the field of empirical asset pricing for their risk premium prediction performance. In this thesis, we build upon the work of [1] by first evaluating models similar to their best performing model in a similar fashion, by using the same dataset and measures, and then expanding upon that. We explore the impact of different feature extraction techniques, ranging from simply removing added complex- ity to representation learning techniques such as incremental PCA and autoen- coders. Furthermore, we also introduce recurrent connections with LSTM and combine them with the earlier mentioned representation learning techniques. We significantly outperform [1] in terms of monthly out-of-sample R2, reach- ing a score of over 3%, by using a condensed version of the dataset, without interaction terms and dummy variables, with a feedforward neural network. However, across the board, all of our models fall short in terms of Sharpe ratio. Even though we find that LSTM works better than the benchmark, it does not outperform the feedforward network using the condensed dataset. We reason that this is because the features already contain a lot of temporal information, such as recent price trends. Overall, the autoencoder based models perform poorly. While the linear incremental PCA based models perform better than the nonlinear autoencoder based ones, they still perform worse than the bench- mark. / Under de senaste åren har maskininlärningsmodeller vunnit kredibilitet inom området empirisk tillgångsvärdering för deras förmåga att förutsäga riskpre- mier. I den här uppsatsen bygger vi på [1]s arbetet genom att först implemente- ra modeller som liknar deras bäst presterande modell och utvärdera dem på ett liknande sätt, genom att använda samma data och mått, och sedan bygga vida- re på det. Vi utforskar effekterna av olika variabelextraktionstekniker, allt från att helt enkelt ta bort extra komplexitet till representationsinlärningstekniker som inkrementell PCA och autoencoders. Vidare introducerar vi även LSTM och kombinerar dem med de tidigare nämnda representationsinlärningstekni- kerna. Min bästa modell presterar betydligt bättre än [1]s i termer av månatlig R2 för testdatan, och når ett resultat på över 3%, genom att använda en kompri- merad version av datan, utan interaktionstermer och dummyvariabler, med ett feedforward neuralt nätverk. Men överlag så brister alla mina modeller i ter- mer av Sharpe ratio. Även om LSTM fungerar bättre än riktvärdet, överträffar det inte feedforward-nätverket med den komprimerade datamängden. Vi re- sonerar att detta är på grund av inputvariablerna som redan innehåller en hel del information över tid, som de senaste pristrenderna. Sammantaget presterar de autoencoderbaserade modellerna dåligt. Även om de linjära inkrementell PCA-baserade modellerna presterar bättre än de olinjära autoencoderbaserade modellerna, presterar de fortfarande sämre än riktvärdet.

Recent progress on deep neural networks has shown remarkable action recognition performance from videos. The remarkable performance is often achieved by transfer learning: training a model on a large-scale labeled dataset (source) and then fine-tuning the model on the small-scale labeled datasets (targets). However, existing action recognition models do not always generalize well on new tasks or datasets because of the following two reasons. i) Current action recognition datasets have a spurious correlation between action types and background scene types. The models trained on these datasets are biased towards the scene instead of focusing on the actual action. This scene bias leads to poor generalization performance. ii) Directly testing the model trained on the source data on the target data leads to poor performance as the source, and target distributions are different. Fine-tuning the model on the target data can mitigate this issue. However, manual labeling small- scale target videos is labor-intensive. In this dissertation, I propose solutions to these two problems. For the first problem, I propose to learn scene-invariant action representations to mitigate the scene bias in action recognition models. Specifically, I augment the standard cross-entropy loss for action classification with 1) an adversarial loss for the scene types and 2) a human mask confusion loss for videos where the human actors are invisible. These two losses encourage learning representations unsuitable for predicting 1) the correct scene types and 2) the correct action types when there is no evidence. I validate the efficacy of the proposed method by transfer learning experiments. I trans- fer the pre-trained model to three different tasks, including action classification, temporal action localization, and spatio-temporal action detection. The results show consistent improvement over the baselines for every task and dataset. I formulate human action recognition as an unsupervised domain adaptation (UDA) problem to handle the second problem. In the UDA setting, we have many labeled videos as source data and unlabeled videos as target data. We can use already exist- ing labeled video datasets as source data in this setting. The task is to align the source and target feature distributions so that the learned model can generalize well on the target data. I propose 1) aligning the more important temporal part of each video and 2) encouraging the model to focus on action, not the background scene, to learn domain-invariant action representations. The proposed method is simple and intuitive while achieving state-of-the-art performance without training on a lot of labeled target videos. I relax the unsupervised target data setting to a sparsely labeled target data setting. Then I explore the semi-supervised video action recognition, where we have a lot of labeled videos as source data and sparsely labeled videos as target data. The semi-supervised setting is practical as sometimes we can afford a little bit of cost for labeling target data. I propose multiple video data augmentation methods to inject photometric, geometric, temporal, and scene invariances to the action recognition model in this setting. The resulting method shows favorable performance on the public benchmarks. / Doctor of Philosophy / Recent progress on deep learning has shown remarkable action recognition performance. The remarkable performance is often achieved by transferring the knowledge learned from existing large-scale data to the small-scale data specific to applications. However, existing action recog- nition models do not always work well on new tasks and datasets because of the following two problems. i) Current action recognition datasets have a spurious correlation between action types and background scene types. The models trained on these datasets are biased towards the scene instead of focusing on the actual action. This scene bias leads to poor performance on the new datasets and tasks. ii) Directly testing the model trained on the source data on the target data leads to poor performance as the source, and target distributions are different. Fine-tuning the model on the target data can mitigate this issue. However, manual labeling small-scale target videos is labor-intensive. In this dissertation, I propose solutions to these two problems. To tackle the first problem, I propose to learn scene-invariant action representations to mitigate background scene- biased human action recognition models for the first problem. Specifically, the proposed method learns representations that cannot predict the scene types and the correct actions when there is no evidence. I validate the proposed method's effectiveness by transferring the pre-trained model to multiple action understanding tasks. The results show consistent improvement over the baselines for every task and dataset. To handle the second problem, I formulate human action recognition as an unsupervised learning problem on the target data. In this setting, we have many labeled videos as source data and unlabeled videos as target data. We can use already existing labeled video datasets as source data in this setting. The task is to align the source and target feature distributions so that the learned model can generalize well on the target data. I propose 1) aligning the more important temporal part of each video and 2) encouraging the model to focus on action, not the background scene. The proposed method is simple and intuitive while achieving state-of-the-art performance without training on a lot of labeled target videos. I relax the unsupervised target data setting to a sparsely labeled target data setting. Here, we have many labeled videos as source data and sparsely labeled videos as target data. The setting is practical as sometimes we can afford a little bit of cost for labeling target data. I propose multiple video data augmentation methods to inject color, spatial, temporal, and scene invariances to the action recognition model in this setting. The resulting method shows favorable performance on the public benchmarks.

<p dir="ltr">Object Recognition and Retrieval is a fundamental problem in Computer Vision that involves recognizing objects and retrieving similar object images through visual queries. While deep metric learning is commonly employed to learn image embeddings for solving such problems, the representations learned using existing methods are not robust to changes in viewpoint, pose, and object state, especially for fine-grained recognition and retrieval tasks. To overcome these limitations, this dissertation aims to learn robust object representations that remain invariant to such transformations for fine-grained tasks. First, it focuses on learning dual pose-invariant embeddings to facilitate recognition and retrieval at both the category and finer object-identity levels by learning category and object-identity specific representations in separate embedding spaces simultaneously. For this, the PiRO framework is introduced that utilizes an attention-based dual encoder architecture and novel pose-invariant ranking losses for each embedding space to disentangle the category and object representations while learning pose-invariant features. Second, the dissertation introduces ranking losses that cluster multi-view images of an object together in both the embedding spaces while simultaneously pulling the embeddings of two objects from the same category closer in the category embedding space to learn fundamental category-specific attributes and pushing them apart in the object embedding space to learn discriminative features to distinguish between them. Third, the dissertation addresses state-invariance and introduces a novel ObjectsWithStateChange dataset to facilitate research in recognizing fine-grained objects with state changes involving structural transformations in addition to pose and viewpoint changes. Fourth, it proposes a curriculum learning strategy to progressively sample object images that are harder to distinguish for training the model, enhancing its ability to capture discriminative features for fine-grained tasks amidst state changes and other transformations. Experimental evaluations demonstrate significant improvements in object recognition and retrieval performance compared to previous methods, validating the effectiveness of the proposed approaches across several challenging datasets under various transformations.</p>

Extraire une représentation de tous les facteurs de haut niveau de l'état d'un agent à partir d'informations sensorielles de bas niveau est une tâche importante, mais difficile, dans l'apprentissage automatique. Dans ce memoire, nous explorerons plusieurs approches non supervisées pour apprendre ces représentations. Nous appliquons et analysons des méthodes d'apprentissage de représentations non supervisées existantes dans des environnements d'apprentissage par renforcement, et nous apportons notre propre suite d'évaluations et notre propre méthode novatrice d'apprentissage de représentations d'état. Dans le premier chapitre de ce travail, nous passerons en revue et motiverons l'apprentissage non supervisé de représentations pour l'apprentissage automatique en général et pour l'apprentissage par renforcement. Nous introduirons ensuite un sous-domaine relativement nouveau de l'apprentissage de représentations : l'apprentissage auto-supervisé. Nous aborderons ensuite deux approches fondamentales de l'apprentissage de représentations, les méthodes génératives et les méthodes discriminatives. Plus précisément, nous nous concentrerons sur une collection de méthodes discriminantes d'apprentissage de représentations, appelées méthodes contrastives d'apprentissage de représentations non supervisées (CURL). Nous terminerons le premier chapitre en détaillant diverses approches pour évaluer l'utilité des représentations. Dans le deuxième chapitre, nous présenterons un article de workshop dans lequel nous évaluons un ensemble de méthodes d'auto-supervision standards pour les problèmes d'apprentissage par renforcement. Nous découvrons que la performance de ces représentations dépend fortement de la dynamique et de la structure de l'environnement. À ce titre, nous déterminons qu'une étude plus systématique des environnements et des méthodes est nécessaire. Notre troisième chapitre couvre notre deuxième article, Unsupervised State Representation Learning in Atari, où nous essayons d'effectuer une étude plus approfondie des méthodes d'apprentissage de représentations en apprentissage par renforcement, comme expliqué dans le deuxième chapitre. Pour faciliter une évaluation plus approfondie des représentations en apprentissage par renforcement, nous introduisons une suite de 22 jeux Atari entièrement labellisés. De plus, nous choisissons de comparer les méthodes d'apprentissage de représentations de façon plus systématique, en nous concentrant sur une comparaison entre méthodes génératives et méthodes contrastives, plutôt que les méthodes générales du deuxième chapitre choisies de façon moins systématique. Enfin, nous introduisons une nouvelle méthode contrastive, ST-DIM, qui excelle sur ces 22 jeux Atari. / Extracting a representation of all the high-level factors of an agent’s state from level-level sensory information is an important, but challenging task in machine learning. In this thesis, we will explore several unsupervised approaches for learning these state representations. We apply and analyze existing unsupervised representation learning methods in reinforcement learning environments, as well as contribute our own evaluation benchmark and our own novel state representation learning method. In the first chapter, we will overview and motivate unsupervised representation learning for machine learning in general and for reinforcement learning. We will then introduce a relatively new subfield of representation learning: self-supervised learning. We will then cover two core representation learning approaches, generative methods and discriminative methods. Specifically, we will focus on a collection of discriminative representation learning methods called contrastive unsupervised representation learning (CURL) methods. We will close the first chapter by detailing various approaches for evaluating the usefulness of representations. In the second chapter, we will present a workshop paper, where we evaluate a handful of off-the-shelf self-supervised methods in reinforcement learning problems. We discover that the performance of these representations depends heavily on the dynamics and visual structure of the environment. As such, we determine that a more systematic study of environments and methods is required. Our third chapter covers our second article, Unsupervised State Representation Learning in Atari, where we try to execute a more thorough study of representation learning methods in RL as motivated by the second chapter. To facilitate a more thorough evaluation of representations in RL we introduce a benchmark of 22 fully labelled Atari games. In addition, we choose the representation learning methods for comparison in a more systematic way by focusing on comparing generative methods with contrastive methods, instead of the less systematically chosen off-the-shelf methods from the second chapter. Finally, we introduce a new contrastive method, ST-DIM, which excels at the 22 Atari games.

Graphs are often considered an excellent way of modeling complex real-world problems since they allow to capture relationships between items. Because of their ubiquity, graph embedding techniques have occupied research groups, seeking how vertices can be encoded into a low-dimensional latent space, useful to then perform machine learning. Recently Graph Neural Networks (GNN) have dominated the space of embeddings generation due to their inherent ability to encode latent node dependencies. Moreover, the newly introduced Inductive Graph Neural Networks gained much popularity for inductively learning and representing node embeddings through neighborhood aggregate measures. Even when an entirely new node, unseen during training, appears in the graph, it can still be properly represented by its neighboring nodes. Although this approach appears suitable for dynamic graphs, available systems and training methodologies are agnostic of dynamicity and solely rely on re-processing full graph snapshots in batches, an approach that has been criticized for its high computational costs. This work provides a thorough solution to this particular problem via an efficient prioritybased method for selecting rehearsed samples that guarantees low complexity and high accuracy. Finally, a data-parallel inference method has been evaluated at scale using Apache Flink, a data stream processor for real-time predictions on high volume graph data streams. / Molti problemi nel mondo reale possono essere rappresentati come grafi poichè queste strutture dati consentono di modellare relazioni tra elementi. A causa del loro vasto uso, molti gruppi di ricerca hanno tentato di rappresentare i vertici in uno spazio a bassa dimensione, utile per poi poter utilizzare tecniche di apprendimento automatico. Le reti neurali per grafi sono state ampiamente utilizzate per via della loro capacità di codificare dipendenze tra vertici. Le reti neurali induttive recentemente introdotte, inoltre, hanno guadagnato popolarità poichè consentono di generare rappresentazioni di vertici aggregando altri vertici. In questo modo anche un nodo completamente nuovo può comunque essere rappresentato utilizzando i suoi nodi vicini. Sebbene questo approccio sia adatto per grafici dinamici, i sistemi ad oggi disponibili e gli algoritmi di addestramento si basano esclusivamente sulla continua elaborazione di grafi statici, un approccio che è stato criticato per i suoi elevati costi di calcolo. Questa tesi fornisce una soluzione a questo problema tramite un metodo efficiente per l’allenamento di reti neurali induttive basato su un’euristica per la selezione dei vertici. Viene inoltre descritto un metodo per eseguire predizioni in modo scalabile in tempo reale utilizzando Apache Flink, un sistema per l’elaborazione di grandi quantità di flussi di dati in tempo reale. / Grafer anses ofta vara ett utmärkt sätt att modellera komplexa problem i verkligheten eftersom de gör det möjligt att fånga relationer mellan objekt. På grund av deras allestädes närhet har grafinbäddningstekniker sysselsatt forskningsgrupper som undersöker hur hörn kan kodas in i ett lågdimensionellt latent utrymme, vilket är användbart för att sedan utföra maskininlärning. Nyligen har Graph Neural Networks (GNN) dominerat utrymmet för inbäddningsproduktion tack vare deras inneboende förmåga att koda latenta nodberoenden. Dessutom fick de nyinförda induktiva grafiska nervnäten stor popularitet för induktivt lärande och representerande nodbäddningar genom sammanlagda åtgärder i grannskapet. Även när en helt ny nod, osynlig under träning, visas i diagrammet, kan den fortfarande representeras ordentligt av dess angränsande noder. Även om detta tillvägagångssätt tycks vara lämpligt för dynamiska grafer, är tillgängliga system och träningsmetodologier agnostiska för dynamik och förlitar sig bara på att behandla fullständiga ögonblicksbilder i partier, en metod som har kritiserats för dess höga beräkningskostnader. Detta arbete ger en grundlig lösning på detta specifika problem via en effektiv prioriteringsbaserad metod för att välja repeterade prover som garanterar låg komplexitet och hög noggrannhet. Slutligen har en dataparallell inferensmetod utvärderats i skala med Apache Flink, en dataströmprocessor för realtidsprognoser för grafiska dataströmmar med hög volym.

No description available.

No description available.