Global ETD Search

261	Deep Learning Based Image Segmentation for Tumor Cell Death Characterization Forsberg, Elise, Resare, Alexander January 2024 (has links) This report presents a deep learning based approach for segmenting and characterizing tumor cell deaths using images provided by the Önfelt lab, which contain NK cells and HL60 leukemia cells. We explore the efficiency of convolutional neural networks (CNNs) in distinguishing between live and dead tumor cells, as well as different classes of cell death. Three CNN architectures: MobileNetV2, ResNet-18, and ResNet-50 were employed, utilizing transfer learning to optimize performance given the limited size of available datasets. The networks were trained using two loss functions: weighted cross-entropy and generalized dice loss and two optimizers: Adaptive moment estimation (Adam) and stochastic gradient descent with momentum (SGDM), with performance evaluations based on metrics such as mean accuracy, intersection over union (IoU), and BF score. Our results indicate that MobileNetV2 with cross-entropy loss and the Adam optimizer outperformed other configurations, demonstrating high mean accuracy. Challenges such as class imbalance, annotation bias, and dataset limitations are discussed, alongside potential future directions to enhance model robustness and accuracy. The successful training of networks capable of classifying all identified types of cell death, demonstrates the potential for a deep learning approach to identify different types of cell deaths as a tool for analyzing immunotherapeutic strategies and enhance understanding of NK cell behaviors in cancer treatment. Deep Learning Image Segmentation Tumor Cells NK Cells Cell Death Characterization Immunotherapy Data Augmentation Convolutional Neural Networks (CNNs) Transfer Learning ResNet MobileNetV2 Optimization Algorithms Physical Sciences Fysik
262	Topics on Machine Learning under Imperfect Supervision Yuan, Gan January 2024 (has links) This dissertation comprises several studies addressing supervised learning problems where the supervision is imperfect. Firstly, we investigate the margin conditions in active learning. Active learning is characterized by its special mechanism where the learner can sample freely over the feature space and exploit mostly the limited labeling budget by querying the most informative labels. Our primary focus is to discern critical conditions under which certain active learning algorithms can outperform the optimal passive learning minimax rate. Within a non-parametric multi-class classification framework,our results reveal that the uniqueness of Bayes labels across the feature space serves as the pivotal determinant for the superiority of active learning over passive learning. Secondly, we study the estimation of central mean subspace (CMS), and its application in transfer learning. We show that a fast parametric convergence rate is achievable via estimating the expected smoothed gradient outer product, for a general class of covariate distribution that admits Gaussian or heavier distributions. When the link function is a polynomial with a degree of at most r and the covariates follow the standard Gaussian, we show that the prefactor depends on the ambient dimension d as d^r. Furthermore, we show that under a transfer learning setting, an oracle rate of prediction error as if the CMS is known is achievable, when the source training data is abundant. Finally, we present an innovative application involving the utilization of weak (noisy) labels for addressing an Individual Tree Crown (ITC) segmentation challenge. Here, the objective is to delineate individual tree crowns within a 3D LiDAR scan of tropical forests, with only 2D noisy manual delineations of crowns on RGB images available as a source of weak supervision. We propose a refinement algorithm designed to enhance the performance of existing unsupervised learning methodologies for the ITC segmentation problem. Statistics Computer science Machine learning--Statistical methods Transfer learning (Machine learning) Active learning Bayesian statistical decision theory Crowns (Botany) Gaussian processes
263	Data Quality Evaluation and Improvement for Machine Learning Chen, Haihua 05 1900 (has links) In this research the focus is on data-centric AI with a specific concentration on data quality evaluation and improvement for machine learning. We first present a practical framework for data quality evaluation and improvement, using a legal domain as a case study and build a corpus for legal argument mining. We first created an initial corpus with 4,937 instances that were manually labeled. We define five data quality evaluation dimensions: comprehensiveness, correctness, variety, class imbalance, and duplication, and conducted a quantitative evaluation on these dimensions for the legal dataset and two existing datasets in the medical domain for medical concept normalization. The first group of experiments showed that class imbalance and insufficient training data are the two major data quality issues that negatively impacted the quality of the system that was built on the legal corpus. The second group of experiments showed that the overlap between the test datasets and the training datasets, which we defined as "duplication," is the major data quality issue for the two medical corpora. We explore several widely used machine learning methods for data quality improvement. Compared to pseudo-labeling, co-training, and expectation-maximization (EM), generative adversarial network (GAN) is more effective for automated data augmentation, especially when a small portion of labeled data and a large amount of unlabeled data is available. The data validation process, the performance improvement strategy, and the machine learning framework for data evaluation and improvement discussed in this dissertation can be used by machine learning researchers and practitioners to build high-performance machine learning systems. All the materials including the data, code, and results will be released at: https://github.com/haihua0913/dissertation-dqei. Data quality data-centric AI machine learning data augmentation transfer learning semi-supervised learning medical concept normalization legal text classification Information Science
264	Исследование задачи построения карты глубины изображения с помощью сверточной нейронной сети : магистерская диссертация / Study of the problem of constructing an image depth map using a convolutional neural network Бакулин, С. А., Bakulin, S. A. January 2024 (has links) Объект исследования: алгоритмы оценки глубины изображения. Предмет исследования: методы обучения и оптимизаций построения карты глубины из одного изображения. Цель работы: оптимизация алгоритма построения карты глубины изображения на основе глубокой нейронной сети. В процессе исследования проводились: сравнение базовых архитектур. модели, анализ и визуализация полученных результатов, измерение производительности различных архитектур, наблюдение за аномальными случаями в процессе обучения и эксплуатации модели. В работе продемонстрирован алгоритм построения, обучения и оптимизации сверточной нейронной сети для оценки глубины изображения. Область практического применения: алгоритмы оценки глубины изображения используются в следующих сферах: беспилотное управление транспортными средствами, 3D реконструкция сцены, AR/VR, навигационные системы, медицина, анимация. / Object of the study: algorithms for estimating the image depth. Subject of the study: methods of training and optimization of constructing a depth map from a single image. Objective of the work: optimization of the algorithm for constructing an image depth map based on a deep neural network. During the study, the following was carried out: comparison of basic architectures. models, analysis and visualization of the obtained results, measurement of the performance of various architectures, observation of anomalous cases during the training and operation of the model. The work demonstrates an algorithm for constructing, training and optimizing a convolutional neural network for estimating the image depth. Area of practical application: image depth estimation algorithms are used in the following areas: unmanned vehicle control, 3D scene reconstruction, AR / VR, navigation systems, medicine, animation. MASTER'S THESIS COMPUTER VISION DEPTH ESTIMATION DEPTH MAP CONVOLUTIONAL NEURAL NETWORKS TRANSFER LEARNING КОМПЬЮТЕРНОЕ ЗРЕНИЕ ОЦЕНКА ГЛУБИНЫ КАРТА ГЛУБИНЫ ПЕРЕНОС ОБУЧЕНИЯ
265	Classification for Diseases in Potatoes Leaf Using Yolov8 : master's thesis Моргуе-Ансах, М., Morgue-Ansah, M. January 2024 (has links) Болезни листьев картофеля представляют значительную угрозу для глобальной продовольственной безопасности, влияя на урожайность и качество. Точные и эффективные методы классификации болезней имеют решающее значение для своевременного вмешательства и управления урожаем. В этом исследовании изучается эффективность современной архитектуры глубокого обучения YOLOv8 для классификации болезней листьев картофеля. Архитектура YOLOv8, известная своими возможностями обнаружения объектов в реальном времени, адаптирована для многоклассовой классификации болезней листьев картофеля. Благодаря трансферному обучению модель предварительно обучается на крупномасштабном наборе данных и настраивается на конкретном наборе данных о болезнях листьев картофеля. YOLOv8 использует одноступенчатую структуру обнаружения объектов, применяя ряд сверточных слоев для обнаружения и классификации болезней непосредственно на изображениях. Аналогичным образом для сравнения использовались Vision Transformers, которые показали многообещающие результаты в задачах классификации изображений. Экспериментальные результаты показали, что YOLOv8 показал точность 97,9%. Набор данных, используемый в этом исследовании, состоит из изображений листьев картофеля с высоким разрешением, пораженных различными болезнями, включая фитофтороз, раннюю гниль и здоровые листья. Для повышения надежности и обобщения модели были применены методы предварительной обработки, такие как дополнение и нормализация данных. Был проведен дополнительный анализ для понимания сильных и слабых сторон каждого подхода. YOLOv8 продемонстрировал превосходную производительность при обнаружении небольших поражений и сложных узоров на листьях картофеля благодаря своим возможностям обнаружения объектов. Это исследование способствует развитию компьютерного зрения в сельском хозяйстве, предоставляя информацию о производительности архитектур глубокого обучения для классификации болезней листьев картофеля. Результаты дают ценное руководство для исследователей и практиков, стремящихся разработать надежные и эффективные системы обнаружения болезней для поддержки устойчивых методов управления урожаем. / Potato leaf diseases pose a significant threat to global food security, affecting yield and quality. Accurate and efficient disease classification methods are crucial for timely intervention and crop management. This study investigates the efficacy state-of-the-art deep learning architecture, YOLOv8 for potato leaf disease classification. The YOLOv8 architecture, renowned for its real-time object detection capabilities, is adapted for multi-class classification of potato leaf diseases. Through transfer learning, the model is pre-trained on a large-scale dataset and fine-tuned on a specific potato leaf disease dataset. YOLOv8 leverages a single-stage object detection framework, employing a series of convolutional layers to detect and classify diseases directly from images. Similarly, Vision Transformers, which have shown promising results in image classification tasks, were employed for comparison. Experimental results revealed that YOLOv8 exhibited an accuracy of 97.9%. The dataset utilized in this research consists of high-resolution images of potato leaves affected by various diseases, including late blight, early blight, and healthy leaves. Preprocessing techniques such as data augmentation and normalization were applied to enhance model robustness and generalization. Further analysis was conducted to understand the strengths and limitations of each approach. YOLOv8 demonstrated superior performance in detecting small lesions and intricate patterns on potato leaves, owing to its object detection capabilities. This study contributes to advancing the field of agricultural computer vision by providing insights into the performance of deep learning architectures for potato leaf disease classification. The findings offer valuable guidance for researchers and practitioners seeking to develop robust and efficient disease detection systems to support sustainable crop management practices. MASTER'S THESIS AGRICULTURAL COMPUTER VISION MACHINE LEARNING TRANSFER LEARNING VISION TRANSFORMERS YOLOV8 МАШИННОЕ ОБУЧЕНИЕ VISION TRANSFORMERS YOLOV8
266	Large-Context Question Answering with Cross-Lingual Transfer Sagen, Markus January 2021 (has links) Models based around the transformer architecture have become one of the most prominent for solving a multitude of natural language processing (NLP)tasks since its introduction in 2017. However, much research related to the transformer model has focused primarily on achieving high performance and many problems remain unsolved. Two of the most prominent currently are the lack of high performing non-English pre-trained models, and the limited number of words most trained models can incorporate for their context. Solving these problems would make NLP models more suitable for real-world applications, improving information retrieval, reading comprehension, and more. All previous research has focused on incorporating long-context for English language models. This thesis investigates the cross-lingual transferability between languages when only training for long-context in English. Training long-context models in English only could make long-context in low-resource languages, such as Swedish, more accessible since it is hard to find such data in most languages and costly to train for each language. This could become an efficient method for creating long-context models in other languages without the need for such data in all languages or pre-training from scratch. We extend the models’ context using the training scheme of the Longformer architecture and fine-tune on a question-answering task in several languages. Our evaluation could not satisfactorily confirm nor deny if transferring long-term context is possible for low-resource languages. We believe that using datasets that require long-context reasoning, such as a multilingual TriviaQAdataset, could demonstrate our hypothesis’s validity. Long-Context Multilingual Model Longformer XLM-R Longformer Long-term Context Extending Context Extend Context Large-Context Long-Context Large Context Long Context Cross-Lingual Multi-Lingual Cross Lingual Multi Lingual QA Question-Answering Question Answering Transformer model Machine Learning Transfer Learning SQuAD Memory Transfer Learning Long-Context Long Context Efficient Monolingual Multilingual QA model Language Model Huggingface BERT RoBERTa XLM-R mBERT Multilingual BERT Efficient Transformers Reformer Linformer Performer Transformer-XL Wikitext-103 TriviaQA HotpotQA WikiHopQA VINNOVA Peltarion AI LM MLM Deep Learning Natural Language Processing NLP Attention Transformers Transfer Learning Datasets Computer and Information Sciences Data- och informationsvetenskap
267	Duplicate Detection and Text Classification on Simplified Technical English / Dublettdetektion och textklassificering på Förenklad Teknisk Engelska Lund, Max January 2019 (has links) This thesis investigates the most effective way of performing classification of text labels and clustering of duplicate texts in technical documentation written in Simplified Technical English. Pre-trained language models from transformers (BERT) were tested against traditional methods such as tf-idf with cosine similarity (kNN) and SVMs on the classification task. For detecting duplicate texts, vector representations from pre-trained transformer and LSTM models were tested against tf-idf using the density-based clustering algorithms DBSCAN and HDBSCAN. The results show that traditional methods are comparable to pre-trained models for classification, and that using tf-idf vectors with a low distance threshold in DBSCAN is preferable for duplicate detection. NLP CNL transformer models LSTM BERT document embeddings word embeddings text classification text clustering transfer learning machine learning Computer Sciences Datavetenskap (datalogi)
268	Multi-object detection and tracking in video sequences / Détection et suivi multi-objets dans des séquences vidéo Mhalla, Ala 04 April 2018 (has links) Le travail développé dans cette thèse porte sur l'analyse de séquences vidéo. Cette dernière est basée sur 3 taches principales : la détection, la catégorisation et le suivi des objets. Le développement de solutions fiables pour l'analyse de séquences vidéo ouvre de nouveaux horizons pour plusieurs applications telles que les systèmes de transport intelligents, la vidéosurveillance et la robotique. Dans cette thèse, nous avons mis en avant plusieurs contributions pour traiter les problèmes de détection et de suivi d'objets multiples sur des séquences vidéo. Les techniques proposées sont basées sur l’apprentissage profonds et des approches de transfert d'apprentissage. Dans une première contribution, nous abordons le problème de la détection multi-objets en proposant une nouvelle technique de transfert d’apprentissage basé sur le formalisme et la théorie du filtre SMC (Sequential Monte Carlo) afin de spécialiser automatiquement un détecteur de réseau de neurones convolutionnel profond (DCNN) vers une scène cible. Dans une deuxième contribution, nous proposons une nouvelle approche de suivi multi-objets original basé sur des stratégies spatio-temporelles (entrelacement / entrelacement inverse) et un détecteur profond entrelacé, qui améliore les performances des algorithmes de suivi par détection et permet de suivre des objets dans des environnements complexes (occlusion, intersection, fort mouvement). Dans une troisième contribution, nous fournissons un système de surveillance du trafic, qui intègre une extension du technique SMC afin d’améliorer la précision de la détection de jour et de nuit et de spécialiser tout détecteur DCNN pour les caméras fixes et mobiles. Tout au long de ce rapport, nous fournissons des résultats quantitatifs et qualitatifs. Sur plusieurs aspects liés à l’analyse de séquences vidéo, ces travaux surpassent les cadres de détection et de suivi de pointe. En outre, nous avons implémenté avec succès nos infrastructures dans une plate-forme matérielle intégrée pour la surveillance et la sécurité du trafic routier. / The work developed in this PhD thesis is focused on video sequence analysis. Thelatter consists of object detection, categorization and tracking. The development ofreliable solutions for the analysis of video sequences opens new horizons for severalapplications such as intelligent transport systems, video surveillance and robotics.In this thesis, we put forward several contributions to deal with the problems ofdetecting and tracking multi-objects on video sequences. The proposed frameworksare based on deep learning networks and transfer learning approaches.In a first contribution, we tackle the problem of multi-object detection by puttingforward a new transfer learning framework based on the formalism and the theoryof a Sequential Monte Carlo (SMC) filter to automatically specialize a Deep ConvolutionalNeural Network (DCNN) detector towards a target scene. The suggestedspecialization framework is used in order to transfer the knowledge from the sourceand the target domain to the target scene and to estimate the unknown target distributionas a specialized dataset composed of samples from the target domain. Thesesamples are selected according to the importance of their weights which reflectsthe likelihood that they belong to the target distribution. The obtained specializeddataset allows training a specialized DCNN detector to a target scene withouthuman intervention.In a second contribution, we propose an original multi-object tracking frameworkbased on spatio-temporal strategies (interlacing/inverse interlacing) and aninterlaced deep detector, which improves the performances of tracking-by-detectionalgorithms and helps to track objects in complex videos (occlusion, intersection,strong motion).In a third contribution, we provide an embedded system for traffic surveillance,which integrates an extension of the SMC framework so as to improve the detectionaccuracy in both day and night conditions and to specialize any DCNN detector forboth mobile and stationary cameras.Throughout this report, we provide both quantitative and qualitative results.On several aspects related to video sequence analysis, this work outperformsthe state-of-the-art detection and tracking frameworks. In addition, we havesuccessfully implemented our frameworks in an embedded hardware platform forroad traffic safety and monitoring. Intelligence artificielle Vision par ordinateur Transfert d'apprentissage Apprentissage profond Détection multi-objets Spécialisation Suivi par détection Suivi multi-objets Système embarqué Artificial intelligence Computer vision Transfer learning Deep learning Multiobject detection Specialization Tracking-by-detection Multi-object tracking Embedded system
269	Extractive Multi-document Summarization of News Articles Grant, Harald January 2019 (has links) Publicly available data grows exponentially through web services and technological advancements. To comprehend large data-streams multi-document summarization (MDS) can be used. In this research, the area of multi-document summarization is investigated. Multiple systems for extractive multi-document summarization are implemented using modern techniques, in the form of the pre-trained BERT language model for word embeddings and sentence classification. This is combined with well proven techniques, in the form of the TextRank ranking algorithm, the Waterfall architecture and anti-redundancy filtering. The systems are evaluated on the DUC-2002, 2006 and 2007 datasets using the ROUGE metric. Where the results show that the BM25 sentence representation implemented in the TextRank model using the Waterfall architecture and an anti-redundancy technique outperforms the other implementations, providing competitive results with other state-of-the-art systems. A cohesive model is derived from the leading system and tried in a user study using a real-world application. The user study is conducted using a real-time news detection application with users from the news-domain. The study shows a clear favour for cohesive summaries in the case of extractive multi-document summarization. Where the cohesive summary is preferred in the majority of cases. NLP extractive summarization multi-document neural embeddings information extraction text-to-text generation textrank BERT attention Transformer transfer learning fine-tuning ROUGE
270	Reinforcement Learning from Demonstration Suay, Halit Bener 25 April 2016 (has links) Off-the-shelf Reinforcement Learning (RL) algorithms suffer from slow learning performance, partly because they are expected to learn a task from scratch merely through an agent's own experience. In this thesis, we show that learning from scratch is a limiting factor for the learning performance, and that when prior knowledge is available RL agents can learn a task faster. We evaluate relevant previous work and our own algorithms in various experiments. Our first contribution is the first implementation and evaluation of an existing interactive RL algorithm in a real-world domain with a humanoid robot. Interactive RL was evaluated in a simulated domain which motivated us for evaluating its practicality on a robot. Our evaluation shows that guidance reduces learning time, and that its positive effects increase with state space size. A natural follow up question after our first evaluation was, how do some other previous works compare to interactive RL. Our second contribution is an analysis of a user study, where na"ive human teachers demonstrated a real-world object catching with a humanoid robot. We present the first comparison of several previous works in a common real-world domain with a user study. One conclusion of the user study was the high potential of RL despite poor usability due to slow learning rate. As an effort to improve the learning efficiency of RL learners, our third contribution is a novel human-agent knowledge transfer algorithm. Using demonstrations from three teachers with varying expertise in a simulated domain, we show that regardless of the skill level, human demonstrations can improve the asymptotic performance of an RL agent. As an alternative approach for encoding human knowledge in RL, we investigated the use of reward shaping. Our final contributions are Static Inverse Reinforcement Learning Shaping and Dynamic Inverse Reinforcement Learning Shaping algorithms that use human demonstrations for recovering a shaping reward function. Our experiments in simulated domains show that our approach outperforms the state-of-the-art in cumulative reward, learning rate and asymptotic performance. Overall we show that human demonstrators with varying skills can help RL agents to learn tasks more efficiently. robotics robots user study lfd rl rlfd artificial intelligence rule learning machine learning policy learning robot learning from demonstration transfer learning agents robot learning learning from demonstration reward shaping reinforcement learning

Search results