Deep learning has dominated the computer vision field since 2012, but a common criticism of deep learning methods is their dependence on large amounts of data. To combat this criticism research into data-efficient deep learning is growing. The foremost success in data-efficient deep learning is transfer learning with networks pre-trained on the ImageNet dataset. Pre-trained networks have achieved state-of-the-art performance on many tasks. We consider the pre-trained network method for a new task where we have to collect the data. We hypothesize that the data efficiency of pre-trained networks can be improved through informed data collection. After exhaustive experiments on CaffeNet and VGG16, we conclude that the data efficiency indeed can be improved. Furthermore, we investigate an alternative approach to data-efficient learning, namely adding domain knowledge in the form of a spatial transformer to the pre-trained networks. We find that spatial transformers are difficult to train and seem to not improve data efficiency.

When classifying texts using a linear classifier, the texts are commonly represented as feature vectors. Previous methods to represent features as vectors have been unable to capture the context of individual words in the texts, in theory leading to a poor representation of natural language. Bidirectional Encoder Representations from Transformers (BERT), uses a multi-headed self-attention mechanism to create deep bidirectional feature representations, able to model the whole context of all words in a sequence. A BERT model uses a transfer learning approach, where it is pre-trained on a large amount of data and can be further fine-tuned for several down-stream tasks. This thesis uses one multilingual, and two dedicated Swedish BERT models, for the task of classifying Swedish texts as of either easy-to-read or standard complexity in their respective domains. The performance on the text classification task using the different models is then compared both with feature representation methods used in earlier studies, as well as with the other BERT models. The results show that all models performed better on the classification task than the previous methods of feature representation. Furthermore, the dedicated Swedish models show better performance than the multilingual model, with the Swedish model pre-trained on more diverse data outperforming the other.

The swift progression of technology has radically reshaped our lives, becoming a big part of our daily routines and paving the way for advancements in communication, automation, and information processing. OpenAI, a company at the forefront of artificial intelligence since 2015, has made remarkable strides towards making AI accessible and beneficial for all (OpenAI, n.d.). A notable accomplishment in their journey has been the development of Chat Generative Pre-trained Transformers (ChatGPT). This study aims to identify and explore the factors influencing students' acceptance and use of ChatGPT in academic settings. Despite the rising prominence of ChatGPT across various disciplines, understanding its acceptance and utilization, particularly within the sphere of higher education, remains limited. ChatGPT holds immense potential as a valuable asset for both students and educators. Utilizing the Unified Theory of Acceptance and Use of Technology (UTAUT) and a quantitative research approach, investigating these factors. The results suggest that student acceptance and use lies in Behavioral Intention, while Behavioral Initiation is influenced by both Effort Expectancy and Performance Expectancy.

The discharge summary is an important document, summarizing a patient’s medical information during their hospital stay. It is crucial for communication between clinicians and primary care physicians. Creating a discharge sum- mary is a necessary task. However, it is time-consuming for physicians. Using technology to automatically generate discharge summaries can be helpful for physicians and assist them in concentrating more on the patients than writing clinical summarization notes and discharge summaries. This master’s thesis aims to contribute to the research of building a transformer-based model for an automated discharge summary with a pre-trained DistilBART language model. This study plans to answer this main research question: How e↵ective is the pre-trained DistilBART language model in predicting an automated discharge summary for multiple clinical texts? The research strategy used in this study is experimental. the dataset is MIMIC- III. To evaluate the e↵ectiveness of the model, ROUGE scores are selected. The result of this model is compared with the result of the baseline BART model, which is implemented on the same dataset in the other recent research. This study regards multiple document summarization as the process of combining multiple inputs into a single input, which is then summarized. The findings indicate an improvement in ROUGE-2 and ROUGE-Lsum in the DistilBART model in comparison with the baseline BART model. However, one important limitation was computational resource constraint. The study also provides eth- ical considerations and some recommendations for future works.

Multilingual natural language processing (NLP) is increasingly recognized for its potential in processing diverse text-type data, including those from social media, reviews, and technical reports. Multilingual language models like mBERT and XLM-RoBERTa (XLM-R) play a pivotal role in multilingual NLP. Notwithstanding their capabilities, the performance of these models largely relies on the availability of annotated training data. This thesis employs the multilingual pre-trained model XLM-R to examine its efficacy in sequence labelling to open-ended questions on democracy across multilingual surveys. Traditional annotation practices have been labour-intensive and time-consuming, with limited automation attempts. Previous studies often translated multilingual data into English, bypassing the challenges and nuances of native languages. Our study explores automatic multilingual annotation at the token level for democracy survey responses in five languages: Hungarian, Italian, Polish, Russian, and Spanish. The results reveal promising F1 scores, indicating the feasibility of using multilingual models for such tasks. However, the performance of these models is closely tied to the quality and nature of the training set. This research paves the way for future experiments and model adjustments, underscoring the importance of refining training data and optimizing model techniques for enhanced classification accuracy.

Nowadays, with the ever growing availability of options in many areas of our lives, it is crucial to have good ways to navigate your choices. This is why recommendation engines’ role is growing more important. Recommenders are often based on user-item interaction. In many areas like news and podcasts, however, by the time there is enough interaction data for an item, the item has already become irrelevant. This is why incorporating content features is desirable, as the content does not depend on the popularity or novelty of an item. Very often, there is text describing an item, so text features are good candidates for features within recommender systems. Within Natural Language Processing (NLP), pre-trained language models based on the Transformer architecture have brought a revolution in recent years, achieving state-of-the-art performance on many language tasks. Because of this, it is natural to explore how such models can play a role within recommendation systems. The scope of this work is on the intersection between NLP and recommendation systems where we investigate what are the effects of adding BERT-based encodings of titles and descriptions of movies and books to a recommender system. The results show that even in off-the-shelf BERT-models there is a considerable amount of information on movie and book similarity. It also shows that BERT based representations could be used in a recommender system for user recommendation to combine the best of collaborative and content representations. In this thesis, it is shown that adding deep pre-trained language model representations could improve a recommender system’s capability to predict good items for users with up to 0.43 AUC-ROC score for a shallow model, and 0.017 AUC-ROC score for a deeper model. It is also shown that SBERT can be fine-tuned to encode item similarity with up to 0.03 nDCG and up to 0.05 nDCG@10 score improvement. / Med den ständigt växande tillgängligheten av val i många delar av våra liv har det blivit viktigt att enkelt kunna navigera kring olika alternativ. Det är därför rekommendationssystems har blivit viktigare. Rekommendationssystem baseras ofta på interaktion-historiken mellan användare och artikel. När tillräckligt mycket data inom nyheter och podcast har hunnits samlats in för att utföra en rekommendation så har artikeln hunnit bli irrelevant. Det är därför det är önskvärt att införa innehållsfunktioner till rekommenderaren, då innehållet inte är beroende av popularitet eller nymodigheten av artikeln. Väldigt ofta finns det text som beskriver en artikel vilket har lett till textfunktioner blivit bra kandidater som funktion för rekommendationssystem. Inom Naturlig Språkbehandling (NLP), har förtränande språkmodeller baserad på transformator arkitekturen revolutionerat området de senaste åren. Den nya arkitekturen har uppnått toppmoderna resultat på flertal språkuppgifter. Tack vare detta, har det blivit naturligt att utforska hur sådana modeller kan fungera inom rekommendationssystem. Det här arbetet är mellan två områden, NLP och rekommendationssystem. Arbetet utforskar effekten av att lägga till BERT-baserade kodningar av titel och beskrivning av filmer, samt böcker till ett rekommendationssystem. Resultaten visar att även i förpackade BERT modeller finns det mycket av information om likheter mellan film och böcker. Resultaten visar även att BERT representationer kan användas i rekommendationssystem för användarrekommendationer, i kombination med kollaborativa och artikel baserade representationer. Uppsatsen visar att lägga till förtränade djupspråkmodell representationer kan förbättra rekommendationssystemens förmåga att förutsäga bra artiklar för användare. Förbättringarna är upp till 0.43 AUC-ROC poäng för en grundmodell, samt 0.017 AUC-ROC poäng för en djupmodell. Uppsatsen visar även att SBERT kan bli finjusterad för att koda artikel likhet med upp till 0.03 nDCG och upp till 0.05 nDCG@10 poängs förbättring.

Les modèles de langue pré-entraînés ont montré leur efficacité dans beaucoup de tâches de traitement de la langue naturelle. Ces modèles peuvent capter des régularités générales d'une langue à partir d'un grand ensemble de textes, qui sont utiles dans la plupart des applications en traitement de langue naturelle. Dans ce mémoire, nous étudions les problèmes de dialogue, i.e. générer une réponse à un énoncé de l'utilisateur. Nous exploitons les modèles de langue pré-entraînés pour traiter différents aspects des systèmes de dialogue. Premièrement, les modèles de langue pré-entraînés sont entraînés and utilisés dans les systèmes de dialogue de différentes façons. Il n'est pas clair quelle façon est la plus appropriée. Pour le dialogue orienté-tâche, l’approche de l'état de l'art pour le suivi de l'état de dialogue (Dialogue State Tracking) utilise BERT comme encodeur et empile un autre réseau de neurones récurrent (RNN) sur les sorties de BERT comme décodeur. Dans ce cas, seul l'encodeur peut bénéficier des modèles de langue pré-entraînés. Dans la première partie de ce mémoire, nous proposons une méthode qui utilise un seul modèle BERT pour l'encodeur et le décodeur, permettant ainsi un ajustement de paramètres plus efficace. Notre méthode atteint une performance qui dépasse l'état de l'art. Pour la tâche de génération de réponses dans un chatbot, nous comparons 4 approches communément utilisées. Elles sont basées sur des modèles pré-entraînés et utilisent des objectifs et des mécanismes d'attention différents. En nous appuyant sur des expérimentations, nous observons l'impact de deux types de disparité qui sont largement ignorées dans la littérature: disparité entre pré-entraînement et peaufinage, et disparité entre peaufinage et génération de réponse. Nous montrons que l'impact de ces disparités devient évident quand le volume de données d’entraînement est limité. Afin de remédier à ce problème, nous proposons deux méthodes qui réduisent les disparités, permettant d'améliorer la performance. Deuxièmement, même si les méthodes basées sur des modèles pré-entraînés ont connu de grands succès en dialogue général, nous devons de plus en plus traiter le problème de dialogue conditionné, c'est-à-dire dialogue en relation à une certaine condition (qui peut désigner un personnage, un sujet, etc.). Des chercheurs se sont aussi intéressés aux systèmes de chatbot avec des habiletés de conversation multiples, i.e. chatbot capable de confronter différentes situations de dialogues conditionnés. Ainsi, dans la seconde partie de ce mémoire, nous étudions le problème de génération de dialogue conditionné. D'abord, nous proposons une méthode générale qui exploite non seulement des données de dialogues conditionnées, mais aussi des données non-dialogues (textes) conditionnées. Ces dernières sont beaucoup plus faciles à acquérir en pratique. Ceci nous permet d'atténuer le problème de rareté de données. Ensuite, nous proposons des méthodes qui utilisent le concept d'adaptateur proposé récemment dans la littérature. Un adaptateur permet de renforcer un système de dialogue général en lui donnant une habileté spécifique. Nous montrons que les adaptateurs peuvent encoder des habiletés de dialogue conditionné de façon stricte ou flexible, tout en utilisant seulement 6% plus de paramètres. Ce mémoire contient 4 travaux sur deux grands problèmes de dialogue: l'architecture inhérente du modèle de dialogue basé sur des modèles de langue pré-entraînés, et l'enrichissement d'un système de dialogue général pour avoir des habiletés spécifiques. Ces travaux non seulement nous permettent d'obtenir des performances dépassant de l'état de l'art, mais aussi soulignent l'importance de concevoir l'architecture du modèle pour bien correspondre à la tâche, plutôt que simplement augmenter le volume de données d'entraînement et la puissance de calcul brute. / Pre-trained language models (LMs) have shown to be effective in many NLP tasks. They can capture general language regularities from a large amount of texts, which are useful for most applications related to natural languages. In this thesis, we study the problems of dialogue, i.e. to generate a response to a user's utterance. We exploit pre-trained language models to deal with different aspects of dialogue systems. First, pre-trained language models have been trained and used in different ways in dialogue systems and it is unclear what is the best way to use pre-trained language models in dialogue. For task-oriented dialogue systems, the state-of-the-art framework for Dialogue State Tracking (DST) uses BERT as the encoder and stacks an RNN upon BERT outputs as the decoder. Pre-trained language models are only leveraged for the encoder. In the first part of the thesis, we investigate methods using a single BERT model for both the encoder and the decoder, allowing for more effective parameter updating. Our method achieves new state-of-the-art performance. For the task of response generation in generative chatbot systems, we further compare the 4 commonly used frameworks based on pre-trained LMs, which use different training objectives and attention mechanisms. Through extensive experiments, we observe the impact of two types of discrepancy: pretrain-finetune discrepancy and finetune-generation discrepancy (i.e. differences between pre-training and fine-tuning, and between fine-tuning and generation), which have not been paid attention to. We show that the impact of the discrepancies will surface when limited amount of training data is available. To alleviate the problem, we propose two methods to reduce discrepancies, yielding improved performance. Second, even though pre-training based methods have shown excellent performance in general dialogue generation, we are more and more faced with the problem of conditioned conversation, i.e. conversation in relation with some condition (persona, topic, etc.). Researchers are also interested in multi-skill chatbot systems, namely equipping a chatbot with abilities to confront different conditioned generation tasks. Therefore, in the second part of the thesis, we investigate the problem of conditioned dialogue generation. First, we propose a general method that leverages not only conditioned dialogue data, but also conditioned non-dialogue text data, which are much easier to collect, in order to alleviate the data scarcity issue of conditioned dialogue generation. Second, the concept of Adapter has been recently proposed, which adapts a general dialogue system to enhance some dialogue skill. We investigate the ways to learn a dialogue skill. We show that Adapter has enough capacity to model a dialogue skill for either loosely-conditioned or strictly-conditioned response generation, while using only 6% more parameters. This thesis contains 4 pieces of work relating to the two general problems in dialogue systems: the inherent architecture for dialogue systems based on pre-trained LMs, and enhancement of a general dialogue system for some specific skills. The studies not only propose new approaches that outperform the current state of the art, but also stress the importance of carefully designing the model architecture to fit the task, instead of simply increasing the amount of training data and the raw computation power.

Eftersom samhället blir allt mer datadrivet revolutionerar användningen av AI och maskininlärning sättet företag fungerar och utvecklas på. Denna studie utforskar användningen av AI, Big Data och Natural Language Processing (NLP) för att förbättra affärsverksamhet och intelligens i företag. Huvudsyftet med denna avhandling är att undersöka om den nuvarande klassificeringsprocessen hos värdorganisationen kan upprätthållas med minskade driftskostnader, särskilt lägre moln-GPU-kostnader. Detta har potential att förbättra klassificeringsmetoden, förbättra produkten som företaget erbjuder sina kunder på grund av ökad klassificeringsnoggrannhet och stärka deras värdeerbjudande. Vidare utvärderas tre tillvägagångssätt mot varandra och implementationerna visar utvecklingen inom området. Modellerna som jämförs i denna studie inkluderar traditionella maskininlärningsmetoder som Support Vector Machine (SVM) och Logistisk Regression, tillsammans med state-of-the-art transformermodeller som BERT, både Pre-Trained och Fine-Tuned. Artikeln visar att det finns en avvägning mellan prestanda och kostnad vilket illustrerar problemet som många företag, som Valu8, står inför när de utvärderar vilket tillvägagångssätt de ska implementera. Denna avvägning diskuteras och analyseras sedan mer detaljerat för att utforska möjliga kompromisser från varje perspektiv i ett försök att hitta en balanserad lösning som kombinerar prestandaeffektivitet och kostnadseffektivitet. / As society is becoming more data-driven, Artificial Intelligence (AI) and Machine Learning are revolutionizing how companies operate and evolve. This study explores the use of AI, Big Data, and Natural Language Processing (NLP) in improving business operations and intelligence in enterprises. The primary objective of this thesis is to examine if the current classification process at the host company can be maintained with reduced operating costs, specifically lower cloud GPU costs. This can improve the classification method, enhance the product the company offers its customers due to increased classification accuracy, and strengthen its value proposition. Furthermore, three approaches are evaluated against each other, and the implementations showcase the evolution within the field. The models compared in this study include traditional machine learning methods such as Support Vector Machine (SVM) and Logistic Regression, alongside state-of-the-art transformer models like BERT, both Pre-Trained and Fine-Tuned. The paper shows a trade-off between performance and cost, showcasing the problem many companies like Valu8 stand before when evaluating which approach to implement. This trade-off is discussed and analyzed in further detail to explore possible compromises from each perspective to strike a balanced solution that combines performance efficiency and cost-effectiveness.

Brain tumor is a disease characterized by uncontrolled growth of abnormal cells inthe brain. The brain is responsible for regulating the functions of all other organs,hence, any atypical growth of cells in the brain can have severe implications for itsfunctions. The number of global mortality in 2020 led by cancerous brains was estimatedat 251,329. However, early detection of brain cancer is critical for prompttreatment and improving patient’s quality of life as well as survival rates. Manualmedical image classification in diagnosing diseases has been shown to be extremelytime-consuming and labor-intensive. Convolutional Neural Networks (CNNs) hasproven to be a leading algorithm in image classification outperforming humans. Thispaper compares five CNN architectures namely: VGG-16, VGG-19, AlexNet, EffecientNetB7,and ResNet-50 in terms of performance and accuracy using transferlearning. In addition, the authors discussed in this paper the economic impact ofCNN, as an AI approach, on the healthcare sector. The models’ performance isdemonstrated using functions for loss and accuracy rates as well as using the confusionmatrix. The conducted experiment resulted in VGG-19 achieving best performancewith 97% accuracy, while EffecientNetB7 achieved worst performance with93% accuracy. / Hjärntumör är en sjukdom som kännetecknas av okontrollerad tillväxt av onormalaceller i hjärnan. Hjärnan är ansvarig för att styra funktionerna hos alla andra organ,därför kan all onormala tillväxt av celler i hjärnan ha allvarliga konsekvenser för dessfunktioner. Antalet globala dödligheten ledda av hjärncancer har uppskattats till251329 under 2020. Tidig upptäckt av hjärncancer är dock avgörande för snabb behandlingoch för att förbättra patienternas livskvalitet och överlevnadssannolikhet.Manuell medicinsk bildklassificering vid diagnostisering av sjukdomar har visat sigvara extremt tidskrävande och arbetskrävande. Convolutional Neural Network(CNN) är en ledande algoritm för bildklassificering som har överträffat människor.Denna studie jämför fem CNN-arkitekturer, nämligen VGG-16, VGG-19, AlexNet,EffecientNetB7, och ResNet-50 i form av prestanda och noggrannhet. Dessutom diskuterarförfattarna i studien CNN:s ekonomiska inverkan på sjukvårdssektorn. Modellensprestanda demonstrerades med hjälp av funktioner om förlust och noggrannhetsvärden samt med hjälp av en Confusion matris. Resultatet av det utfördaexperimentet har visat att VGG-19 har uppnått bästa prestanda med 97% noggrannhet,medan EffecientNetB7 har uppnått värsta prestanda med 93% noggrannhet.

Les changements climatiques et les phénomènes météorologiques extrêmes sont devenus des moteurs importants de changements de la biodiversité, posant une menace pour la perte d’habitat et l’extinction d’espèces. Comprendre l’état actuel de la biodiversité et identifier les zones hautement adaptées (still strugling with this expression, high suitability for who or what?) sont essentiels afin de lutter contre la perte de biodiversité et guider les processus décisionnels en lien avec les études scientifiques (added scientifiques, as in scientific surveys), les mesures de protection et les efforts de restauration. Les modèles de distribution des espèces (MDE ou SDM en anglais) sont des outils statistiques permettant de prédire la distribution géographique potentielle d’une espèce en fonction de variables environnementales et des données recueillies à cet endroit. Cependant, les MDE conventionnels sont souvent confrontés à des limitations dues à la résolution spatiale et à la couverture restreinte des variables environnementales, lesquelles sont obtenues suite à des mesures au sol ou à l’aide de stations météorologiques. Pour mieux comprendre la distribution des espèces à des fins de conservation, le défi GeoLifeCLEF 2022 a été organisé. Cette compétiion comprend un vaste ensemble de données composé de 1,6 million géo-observations liées à la présence de 17 000 espèces végétales et animales. L’objectif principal de ce défi est d’explorer le potentiel des données de télédétection afin de prédire la présence d’espèces à des géolocalisations spécifiques. Dans ce mémoire, nous étudions diverses techniques d’apprentissage automatique et leur performance en lien avec le défi GeoLifeCLEF 2022. Nous explorons l’efficacité d’algorithmes bien connus en apprentissage par transfert, établissons un cadre d’apprentissage non supervisé et étudions les approches d’apprentissage auto-supervisé lors de la phase d’entraînement. Nos résultats démontrent qu’un ajustement fin des encodeurs pré-entraînés sur différents domaines présente les résultats les plus prometteurs lors de la phase de test. / Climate change and extreme weather events have emerged as significant drivers of biodiversity changes, posing a threat of habitat loss and species extinction. Understanding the current state of biodiversity and identifying areas with high suitability for different species are vital in combating biodiversity loss and guiding decision-making processes for protective measures and restoration efforts. Species distribution models (SDMs) are statistical tools for predicting a species' potential geographic distribution based on environmental variables and occurrence data. However, conventional SDMs often face limitations due to the restricted spatial resolution and coverage of environmental variables derived from ground-based measurements or weather station data. To better understand species distribution for conservation purposes, the GeoLifeCLEF 2022 challenge was introduced. This competition encompasses a large dataset of 1.6 million geo-observations linked to the presence of 17,000 plant and animal species. The primary objective of this challenge is to explore the potential of remote sensing data in forecasting species' presence at specific geolocations. In this thesis, we investigate various machine learning techniques and their performance on the GeoLifeCLEF 2022 challenge. We explore the effectiveness of standard transfer learning algorithms, establish an unsupervised learning framework, and investigate self-supervised learning approaches for training. Our findings demonstrate that fine-tuning pre-trained encoders on different domains yields the most promising test set performance results.