Academic literature on the topic 'Deep active learning'

Deep meaningful learning is the higher-order thinking and development through manifold active intellectual engagement aiming at meaning construction through pattern recognition and concept association. It includes inquiry, critical thinking, creative thinking, problem-solving, and metacognitive skills. It is a theory with a long academic record that can accommodate the demand for excellence in teaching and learning at all levels of education. Its achievement is verified through knowledge application in authentic contexts.

Most of the current object detection approaches deliver competitive results with an assumption that a large number of labeled data are generally available and can be fed into a deep network at once. However, due to expensive labeling efforts, it is difficult to deploy the object detection systems into more complex and challenging real-world environments, especially for defect detection in real industries. In order to reduce the labeling efforts, this study proposes an active learning framework for defect detection. First, an Uncertainty Sampling is proposed to produce the candidate list for annotation. Uncertain images can provide more informative knowledge for the learning process. Then, an Average Margin method is designed to set the sampling scale for each defect category. In addition, an iterative pattern of training and selection is adopted to train an effective detection model. Extensive experiments demonstrate that the proposed method can render the required performance with fewer labeled data.

Solar eruptive events could affect radio communication, global positioning systems, and some high-tech equipment in space. Active regions on the Sun are the main source regions of solar eruptive events. Therefore, the automatic detection of active regions is important not only for routine observation, but also for the solar activity forecast. At present, active regions are manually or automatically extracted by using traditional image processing techniques. Because active regions dynamically evolve, it is not easy to design a suitable feature extractor. In this paper, we first overview the commonly used methods for active region detection currently. Then, two representative object detection models, faster R-CNN and YOLO V3, are employed to learn the characteristics of active regions, and finally establish a deep learning–based detection model of active regions. The performance evaluation demonstrates that the high accuracy of active region detection is achieved by both the two models. In addition, YOLO V3 is 4% and 1% better than faster R-CNN in terms of true positive (TP) and true negative (TN) indexes, respectively; meanwhile, the former is eight times faster than the latter.

Multiview active learning (MAL) is a technique which can achieve a large decrease in the size of the version space than traditional active learning and has great potential applications in large-scale data analysis. In this paper, we present a new deep multiview active learning (DMAL) framework which is the first to combine multiview active learning and deep learning for annotation effort reduction. In this framework, our approach advances the existing active learning methods in two aspects. First, we incorporate two different deep convolutional neural networks into active learning which uses multiview complementary information to improve the feature learnings. Second, through the properly designed framework, the feature representation and the classifier can be simultaneously updated with progressively annotated informative samples. The experiments with two challenging image datasets demonstrate that our proposed DMAL algorithm can achieve promising results than several state-of-the-art active learning algorithms.

Depth estimation using stereo images is an important task in many computer vision applications. A stereo camera contains two image sensors that observe the scene from slightly different viewpoints, making it possible to find the depth of the scene. An active stereo camera also uses a laser projector that projects a pattern into the scene. The advantage of the laser pattern is the additional texture that gives better depth estimations in dark and textureless areas.  Recently, deep learning methods have provided new solutions producing state-of-the-art performance in stereo reconstruction. The aim of this project was to investigate the behavior of a deep learning model for active stereo reconstruction, when using data from different cameras. The model is self-supervised, which solves the problem of having enough ground truth data for training the model. It instead uses the known relationship between the left and right images to let the model learn the best estimation. The model was separately trained on datasets from three different active stereo cameras. The three trained models were then compared using evaluation images from all three cameras. The results showed that the model did not always perform better on images from the camera that was used for collecting the training data. However, when comparing the results of different models using the same test images, the model that was trained on images from the camera used for testing gave better results in most cases.

Les thèmes principaux abordés dans cette thèse sont l'utilisation de méthodes d'apprentissage actif et d'apprentissage profond dans le contexte du traitement de documents multimodaux. Les contributions proposées dans cette thèse abordent ces deux thèmes. Un système d'apprentissage actif a été introduit pour permettre une annotation plus efficace des émissions de télévision grâce à la propagation des étiquettes, à l'utilisation de données multimodales et à des stratégies de sélection efficaces. Plusieurs scénarios et expériences ont été envisagés dans le cadre de l'identification des personnes dans les vidéos, en prenant en compte l'utilisation de différentes modalités (telles que les visages, les segments de la parole et le texte superposé) et différentes stratégies de sélection. Le système complet a été validé au cours d'un ``test à blanc'' impliquant des annotateurs humains réels.Une deuxième contribution majeure a été l'étude et l'utilisation de l'apprentissage profond (en particulier les réseaux de neurones convolutifs) pour la recherche d'information dans les vidéos. Une étude exhaustive a été réalisée en utilisant différentes architectures de réseaux neuronaux et différentes techniques d'apprentissage telles que le réglage fin (fine-tuning) ou des classificateurs plus classiques comme les SVMs. Une comparaison a été faite entre les caractéristiques apprises (la sortie des réseaux neuronaux) et les caractéristiques plus classiques (``engineered features''). Malgré la performance inférieure des seconds, une fusion de ces deux types de caractéristiques augmente la performance globale.Enfin, l'utilisation d'un réseau neuronal convolutif pour l'identification des locuteurs à l'aide de spectrogrammes a été explorée. Les résultats ont été comparés à ceux obtenus avec d'autres systèmes d'identification de locuteurs récents. Différentes approches de fusion ont également été testées. L'approche proposée a permis d'obtenir des résultats comparables à ceux certains des autres systèmes testés et a offert une augmentation de la performance lorsqu'elle est fusionnée avec la sortie du meilleur système
The main topics of this thesis include the use of active learning-based methods and deep learning in the context of retrieval of multimodal documents. The contributions proposed during this thesis address both these topics. An active learning framework was introduced, which allows for a more efficient annotation of broadcast TV videos thanks to the propagation of labels, the use of multimodal data and selection strategies. Several different scenarios and experiments were considered in the context of person identification in videos, including using different modalities (such as faces, speech segments and overlaid text) and different selection strategies. The whole system was additionally validated in a dry run involving real human annotators.A second major contribution was the investigation and use of deep learning (in particular the convolutional neural network) for video retrieval. A comprehensive study was made using different neural network architectures and training techniques such as fine-tuning or using separate classifiers like SVM. A comparison was made between learned features (the output of neural networks) and engineered features. Despite the lower performance of the engineered features, fusion between these two types of features increases overall performance.Finally, the use of convolutional neural network for speaker identification using spectrograms is explored. The results are compared to other state-of-the-art speaker identification systems. Different fusion approaches are also tested. The proposed approach obtains comparable results to some of the other tested approaches and offers an increase in performance when fused with the output of the best system

In this paper, we propose a novel active learning algorithm for short-text (Chinese) classification applied to a deep learning architecture. This topic thus belongs to a cross research area between active learning and deep learning. One of the bottlenecks of deeplearning for classification is that it relies on large number of labeled samples, which is expensive and time consuming to obtain. Active learning aims to overcome this disadvantage through asking the most useful queries in the form of unlabeled samples to belabeled. In other words, active learning intends to achieve precise classification accuracy using as few labeled samples as possible. Such ideas have been investigated in conventional machine learning algorithms, such as support vector machine (SVM) for imageclassification, and in deep neural networks, including convolutional neural networks (CNN) and deep belief networks (DBN) for image classification. Yet the research on combining active learning with recurrent neural networks (RNNs) for short-text classificationis rare. We demonstrate results for short-text classification on datasets from Zhuiyi Inc. Importantly, to achieve better classification accuracy with less computational overhead,the proposed algorithm shows large reductions in the number of labeled training samples compared to random sampling. Moreover, the proposed algorithm is a little bit better than the conventional sampling method, uncertainty sampling. The proposed activelearning algorithm dramatically decreases the amount of labeled samples without significantly influencing the test classification accuracy of the original RNNs classifier, trainedon the whole data set. In some cases, the proposed algorithm even achieves better classification accuracy than the original RNNs classifier.
I detta arbete studerar vi en ny aktiv inlärningsalgoritm som appliceras på en djup inlärningsarkitektur för klassificering av korta (kinesiska) texter. Ämnesområdet hör därmedtill ett ämnesöverskridande område mellan aktiv inlärning och inlärning i djupa nätverk .En av flaskhalsarna i djupa nätverk när de används för klassificering är att de beror avtillgången på många klassificerade datapunkter. Dessa är dyra och tidskrävande att skapa. Aktiv inlärning syftar till att överkomma denna typ av nackdel genom att generera frågor rörande de mest informativa oklassade datapunkterna och få dessa klassificerade. Aktiv inlärning syftar med andra ord till att uppnå bästa klassificeringsprestanda medanvändandet av så få klassificerade datapunkter som möjligt. Denna idé har studeratsinom konventionell maskininlärning, som tex supportvektormaskinen (SVM) för bildklassificering samt inom djupa neuronnätverk inkluderande bl.a. convolutional networks(CNN) och djupa beliefnetworks (DBN) för bildklassificering. Emellertid är kombinationenav aktiv inlärning och rekurrenta nätverk (RNNs) för klassificering av korta textersällsynt. Vi demonstrerar här resultat för klassificering av korta texter ur en databas frånZhuiyi Inc. Att notera är att för att uppnå bättre klassificeringsnoggranhet med lägre beräkningsarbete (overhead) så uppvisar den föreslagna algoritmen stora minskningar i detantal klassificerade träningspunkter som behövs jämfört med användandet av slumpvisadatapunkter. Vidare, den föreslagna algoritmen är något bättre än den konventionellaurvalsmetoden, osäkherhetsurval (uncertanty sampling). Den föreslagna aktiva inlärningsalgoritmen minska dramatiskt den mängd klassificerade datapunkter utan att signifikant påverka klassificeringsnoggranheten hos den ursprungliga RNN-klassificeraren när den tränats på hela datamängden. För några fall uppnår den föreslagna algoritmen t.o.m.bättre klassificeringsnoggranhet än denna ursprungliga RNN-klassificerare.

Relatively recent progress in object detection can mainly be attributed to the success of deep neural networks. However, training such models requires large amounts of annotated data. This poses a two-fold problem, namely obtaining labelled data is a time-consuming process, and training models on many instances is computationally costly. To this end a common approach is to employ active learning, which amounts to constructing a strategy to interactively query much fewer data points while maximizing the performance. In the context of deep object detection in videos, two new challenges arise. Firstly, common uncertainty-based query strategies depend on the quality of uncertainty estimates, which often require special treatment for deep neural networks. Secondly, the nature of batch-based training calls for querying subsets of images, which due to inherent temporal similarity may lack informativeness to increase performance. In this work we attempt to remedy both issues by proposing strategies relying on improved uncertainty estimates and diversification methods. Experiments show that our proposed uncertainty-based strategies are comparable to a random baseline, while the diversity-based ones, conditioned on improved uncertainty estimates, yield significantly better performance than the baseline. In particular, our best strategy using only 15% of data comes to as close as 90:27% of the performance when using all the available data to train the detector.
De senaste framstegen inom objektdetektering kan till största delen tillskrivas djupa neurala nätverk. Träning av sådana modeller kräver dock stora mängder annoterad data. Detta utgör ett två-faldigt problem; att få tag i annoterad data är en tidskrävande process och själva träningen är i många fall beräkningsmässigt kostsam. En vanlig approach för att åtgärda dessa problem är att använda så kallad aktiv inlärning, vilket innebär att man skapar en strategi för att interaktivt välja ut och använda betydligt färre datapunkter samtidigt som prestandan maximeras. I samband med djup objektdetektering på videodata så uppstår två nya utmaningar. För det första så beror typiska osäkerhetsbaserade strategier på kvaliteten på osäkerhetsuppskattningarna, vilka ofta kräver särskild behandling av djupa neurala nätverk. För det andra, om karaktären av batch-baserad träning och likhet mellan bilder i en videosekvens ej beaktas kan det resultera i icke-informativa samlingar av datapunkter som saknar mångfald. I detta arbete försöker vi åtgärda båda problemen genom att föreslå strategier som bygger på förbättrade osäkerhetsuppskattningar och diversifieringsmetoder. Empiriska experiment demonstrerar att våra föreslagna osäkerhetsbaserade strategier är jämförbara med en referensmetod som väljer ut datapunkter slumpmässigt medan diversifieringsstrategierna, givet förbättrade osäkerhetsuppskattningar, ger betydligt bättre prestanda än referensmetoden. Noterbart är att med endast 15% av datamängden når vår bästa strategi så mycket som 90:27% av prestandan som när man använder all tillgänglig data för att träna detektorn.

Deep learning networks are nowadays a major asset for smart city applications and brand new technologies. It is well known that deep learning methods require a great amount of data to have good performance, especially for safety-critical applications such as autonomous driving. Therefore reducing the expensive and time-consuming labelling task done by human annotators is a hot topic. Being one of the most promising candidates to solve this problem, active learning aims to reduce drastically the number of samples to annotate for the learning process. In this work, we focus on the design of an active learning strategy in the specific context of object detection in videos. Besides traditional criteria of sampling, the queries are evaluated based on the temporal coherence of the network’s predictions. Introduced very recently, this characteristic has proven itself to be efficient for evaluating the informativeness of data points. Introducing Temporal Flow, we tested our sampling strategy against the state of the art methods and outperformed them on a benchmark dataset. Indeed, our active learning showed better average performance per labelled samples after each cycle of training. The promising results are encouraging to pursue the effort done in active learning for object detection in videos. A real implementation of this work is feasible but also more research can follow as we acknowledge that further improvements are possible.
Djupinlärning är idag en viktig tillgång för tillämpningar i den smarta staden och annan ny teknik. Det är välkänt att djupa inlärningsmetoder kräver stora mängder data för att uppnå bra prestanda, särskilt för säkerhetskritiska applikationer som autonom körning. Att försöka minska mängden dyr och tidskrävande annotering som utförs av människor är ett hett ämne. En av de mest lovande kandidaterna för att lösa detta problem är aktiv inlärning. I detta arbete fokuserar vi på utformningen av en strategi för aktiv inlärning i ett specifikt sammanhang, detektion av objekt i video. Förutom traditionella kriterier för sampling, utvärderas den temporära koherensen i nätverkets förutsägelser. Denna nyligen introducerade egenskap har visat sig vara effektiv för att utvärdera informationsinnehållet hos datapunkter. Detta arbete introducerar vår metod Temporal Flow. Vi testade vår samplingsstrategi mot de modernaste metoderna och överträffade dem vid jämförelse på ett benchmarking-dataset. Resultaten uppmuntrar en fortsättning av ansträngningarna som gjorts i aktiv inlärning för objektdetektering i videor.
Les réseaux de neurones sont aujourd’hui un atout majeur pour les applications en Smart City et autres nouvelles technologies. Il est bien connu que ces méthodes nécessitent une grande quantité de données pour avoir de bonnes performances, notamment en matière de sécurité pour des applications critiques telles que la conduite autonome. Par conséquent, la réduction de la longue et coûteuse tâche d’annotation effectuée par les annotateurs humains est un sujet de recherche prisé. Étant l’un des candidats les plus prometteurs pour pallier à cela, l’active learning vise à réduire considérablement le nombre d’échantillons à annoter pour le processus d’apprentissage. Dans ce travail, nous nous concentrons sur la conception d’une stratégie d’active learning dans le contexte spécifique de la détection d’objets dans les vidéos. Outre les critères traditionnels d’échantillonnage, les requêtes évaluent la cohérence temporelle des prédictions. Introduite très récemment, cette caractéristique s’est révélée efficace pour évaluer le caractère informatif des points de données. En introduisant Temporal Flow, nous avons testé notre stratégie d’échantillonnage par rapport aux méthodes faisant état de l’art et les avons surpassé sur un dataset de référence. Les résultats prometteurs sont encourageants pour poursuivre l’effort entrepris en active learning pour la détection d’objets dans les vidéos. Une véritable mise en oeuvre de ce travail est faisable, mais des recherches plus avancées peuvent également suivre, comme nous reconnaissons que des améliorations peuvent être apportées.

Convolutional Neural Networks (CNNs) have been proved to deliver great results in the area of computer vision, however, one fundamental bottleneck with CNNs is the fact that it is heavily dependant on the ground truth, that is, labeled training data. A labeled dataset is a group of samples that have been tagged with one or more labels. In this degree project, we mitigate the data greedy behavior of CNNs by applying deep active learning with various kinds of sampling strategies. The main focus will be on the sampling strategies random sampling, least confidence sampling, margin sampling, entropy sampling, and K- means sampling. We choose to study the random sampling strategy since it will work as a baseline to the other sampling strategies. Moreover, the least confidence sampling, margin sampling, and entropy sampling strategies are uncertainty based sampling strategies, hence, it is interesting to study how they perform in comparison with the geometrical based K- means sampling strategy. These sampling strategies will help to find the most informative/representative samples amongst all unlabeled samples, thus, allowing us to label fewer samples. Furthermore, the benchmark datasets MNIST and CIFAR10 will be used to verify the performance of the various sampling strategies. The performance will be measured in terms of accuracy and less data needed. Lastly, we concluded that by using least confidence sampling and margin sampling we reduced the number of labeled samples by 79.25% in comparison with the random sampling strategy for the MNIST dataset. Moreover, by using entropy sampling we reduced the number of labeled samples by 67.92% for the CIFAR10 dataset.
Faltningsnätverk har visat sig leverera bra resultat inom området datorseende, men en fundamental flaskhals med Faltningsnätverk är det faktum att den är starkt beroende av klassificerade datapunkter. I det här examensarbetet hanterar vi Faltningsnätverkens giriga beteende av klassificerade datapunkter genom att använda deep active learning med olika typer av urvalsstrategier. Huvudfokus kommer ligga på urvalsstrategierna slumpmässigt urval, minst tillförlitlig urval, marginal baserad urval, entropi baserad urval och K- means urval. Vi väljer att studera den slumpmässiga urvalsstrategin eftersom att den kommer användas för att mäta prestandan hos de andra urvalsstrategierna. Dessutom valde vi urvalsstrategierna minst tillförlitlig urval, marginal baserad urval, entropi baserad urval eftersom att dessa är osäkerhetsbaserade strategier som är intressanta att jämföra med den geometribaserade strategin K- means. Dessa urvalsstrategier hjälper till att hitta de mest informativa/representativa datapunkter bland alla oklassificerade datapunkter, vilket gör att vi behöver klassificera färre datapunkter. Vidare kommer standard dastaseten MNIST och CIFAR10 att användas för att verifiera prestandan för de olika urvalsstrategierna. Slutligen drog vi slutsatsen att genom att använda minst tillförlitlig urval och marginal baserad urval minskade vi mängden klassificerade datapunkter med 79, 25%, i jämförelse med den slumpmässiga urvalsstrategin, för MNIST- datasetet. Dessutom minskade vi mängden klassificerade datapunkter med 67, 92% med hjälp av entropi baserad urval för CIFAR10datasetet.

The interest for autonomous driving assistance, and in the end, self-driving cars, has increased vastly over the last decade. Automotive safety continues to be a priority for manufacturers, politicians and people alike. Visual-based systems aiding the drivers have lately been boosted by advances in computer vision and machine learning. In this thesis, we evaluate the concept of an end-to-end machine learning solution for detecting and classifying road lane markings, and compare it to a more classical semantic segmentation solution. The analysis is based on the frame-by-frame scenario, and shows that our proposed end-to-end system has clear advantages when it comes detecting the existence of lanes and producing a consistent, lane-like output, especially in adverse conditions such as weak lane markings. Our proposed method allows the system to predict its own confidence, thereby allowing the system to suppress its own output when it is not deemed safe enough. The thesis finishes with proposed future work needed to achieve optimal performance and create a system ready for deployment in an active safety product.

With cancer being one of the leading causes of death globally, and with oral cancers being among the most common types of cancer, it is of interest to conduct large-scale oral cancer screening among the general population. Deep Learning can be used to make this possible despite the medical expertise required for early detection of oral cancers. A bottleneck of Deep Learning is the large amount of data required to train a good model. This project investigates two topics: certainty calibration, which aims to make a machine learning model produce more reliable predictions, and Active Learning, which aims to reduce the amount of data that needs to be labeled for Deep Learning to be effective. In the investigation of certainty calibration, five different methods are compared, and the best method is found to be Dirichlet calibration. The Active Learning investigation studies a single method, Cost-Effective Active Learning, but it is found to produce poor results with the given experiment setting. These two topics inspire the further development of the cytological annotation tool CytoBrowser, which is designed with oral cancer data labeling in mind. The proposedevolution integrates into the existing tool a Deep Learning-assisted annotation workflow that supports multiple users.

In recent years, development of Convolutional Neural Networks has enabled high performing semantic segmentation models. Generally, these deep learning based segmentation methods require a large amount of annotated data. Acquiring such annotated data for semantic segmentation is a tedious and expensive task. Within machine learning, active learning involves in the selection of new data in order to limit the usage of annotated data. In active learning, the model is trained for several iterations and additional samples are selected that the model is uncertain of. The model is then retrained on additional samples and the process is repeated again. In this thesis, an active learning framework has been applied to road segmentation which is semantic segmentation of objects related to road scenes. The uncertainty in the samples is estimated with Monte Carlo dropout. In Monte Carlo dropout, several dropout masks are applied to the model and the variance is captured, working as an estimate of the model’s uncertainty. Other metrics to rank the uncertainty evaluated in this work are: a baseline method that selects samples randomly, the entropy in the default predictions and three additional variations/extensions of Monte Carlo dropout. Both the active learning framework and uncertainty estimation are implemented in the thesis. Monte Carlo dropout performs slightly better than the baseline in 3 out of 4 metrics. Entropy outperforms all other implemented methods in all metrics. The three additional methods do not perform better than Monte Carlo dropout. An analysis of what kind of uncertainty Monte Carlo dropout capture is performed together with a comparison of the samples selected by baseline and Monte Carlo dropout. Future development and possible improvements are also discussed.

Remote sensing data has great potential for wildfire detection and monitoring with enhanced spatial resolution and temporal coverage. Earth Observation satellites have been employed to systematically monitor fire activity over large regions in two ways: (i) to detect the location of actively burning spots (during the fire event), and (ii) to map the spatial extent of the burned scars (during or after the event). Active fire detection plays an important role in wildfire early warning systems. The open-access of Sentinel-2 multispectral data at 20-m resolution offers an opportunity to evaluate its complementary role to the coarse indication in the hotspots provided by MODIS-like polar-orbiting and GOES-like geostationary systems. In addition, accurate and timely mapping of burned areas is needed for damage assessment. Recent advances in deep learning (DL) provides the researcher with automatic, accurate, and bias-free large-scale mapping options for burned area mapping using uni-temporal multispectral imagery. Therefore, the objective of this thesis is to evaluate multispectral remote sensing data (in particular Sentinel-2) for wildfire detection, including active fire detection using a multi-criteria approach and burned area detection using DL models.        For active fire detection, a multi-criteria approach based on the reflectance of B4, B11, and B12 of Sentinel-2 MSI data is developed for several representative fire-prone biomes to extract unambiguous active fire pixels. The adaptive thresholds for each biome are statistically determined from 11 million Sentinel-2 observations samples acquired over summertime (June 2019 to September 2019) across 14 regions or countries. The primary criterion is derived from 3 sigma prediction interval of OLS regression of observation samples for each biome. More specific criteria based on B11 and B12 are further introduced to reduce the omission errors (OE) and commission errors (CE).        The multi-criteria approach proves to be effective in cool smoldering fire detection in study areas with tropical & subtropical grasslands, savannas & shrublands using the primary criterion. At the same time, additional criteria that thresholds the reflectance of B11 and B12 can effectively decrease the CE caused by extremely bright flames around the hot cores in testing sites with Mediterranean forests, woodlands & scrub. The other criterion based on reflectance ratio between B12 and B11 also avoids the effects of CE caused by hot soil pixels in sites with tropical & subtropical moist broadleaf forests. Overall, the validation performance over testing patches reveals that CE and OE can be kept at a low level  (0.14 and 0.04) as an acceptable trade-off. This multi-criteria algorithm is suitable for rapid active fire detection based on uni-temporal imagery without the requirement of multi-temporal data. Medium-resolution multispectral data can be used as a complementary choice to the coarse resolution images for their ability to detect small burning areas and to detect active fires more accurately.        For burned area mapping, this thesis aims to expound on the capability of deep DL models for automatically mapping burned areas from uni-temporal multispectral imagery. Various burned area detection algorithms have been developed using Sentinel-2 and/or Landsat data, but most of the studies require a pre-fire image, dense time-series data, or an empirical threshold. In this thesis, several semantic segmentation network architectures, i.e., U-Net, HRNet, Fast- SCNN, and DeepLabv3+ are applied to Sentinel-2 imagery and Landsat-8 imagery over three testing sites in two local climate zones. In addition, three popular machine learning (ML) algorithms (LightGBM, KNN, and random forests) and NBR thresholding techniques (empirical and OTSU-based) are used in the same study areas for comparison.        The validation results show that DL algorithms outperform the machine learning (ML) methods in two of the three cases with the compact burned scars,  while ML methods seem to be more suitable for mapping dispersed scar in boreal forests. Using Sentinel-2 images, U-Net and HRNet exhibit comparatively identical performance with higher kappa (around 0.9) in one heterogeneous Mediterranean fire site in Greece; Fast-SCNN performs better than others with kappa over 0.79 in one compact boreal forest fire with various burn severity in Sweden. Furthermore, directly transferring the trained models to corresponding Landsat-8 data, HRNet dominates in the three test sites among DL models and can preserve the high accuracy. The results demonstrate that DL models can make full use of contextual information and capture spatial details in multiple scales from fire-sensitive spectral bands to map burned areas. With the uni-temporal image, DL-based methods have the potential to be used for the next Earth observation satellite with onboard data processing and limited storage for previous scenes.    In the future study, DL models will be explored to detect active fire from multi-resolution remote sensing data. The existing problem of unbalanced labeled data can be resolved via advanced DL architecture, the suitable configuration on the training dataset, and improved loss function. To further explore the damage caused by wildfire, future work will focus on the burn severity assessment based on DL models through multi-class semantic segmentation. In addition, the translation between optical and SAR imagery based on Generative Adversarial Network (GAN) model could be explored to improve burned area mapping in different weather conditions.
Fjärranalysdata har stor potential för upptäckt och övervakning av skogsbränder med förbättrad rumslig upplösning och tidsmässig täckning. Jordobservationssatelliter har använts för att systematiskt övervaka brandaktivitet över stora regioner på två sätt: (i) för att upptäcka placeringen av aktivt brinnande fläckar (under brandhändelsen) och (ii) för att kartlägga den brända ärrens rumsliga omfattning ( under eller efter evenemanget). Aktiv branddetektering spelar en viktig roll i system för tidig varning för skogsbränder. Den öppna tillgången till Sentinel-2 multispektral data vid 20 m upplösning ger en möjlighet att utvärdera dess kompletterande roll i förhållande till den grova indikationen i hotspots som tillhandahålls av MODIS-liknande polaromloppsbanesystem och GOES-liknande geostationära system. Dessutom krävs en korrekt och snabb kartläggning av brända områden för skadebedömning. Senaste framstegen inom deep learning (DL) ger forskaren automatiska, exakta och förspänningsfria storskaliga kartläggningsalternativ för kartläggning av bränt område med unitemporal multispektral bild. Därför är syftet med denna avhandling att utvärdera multispektral fjärranalysdata (särskilt Sentinel- 2) för att upptäcka skogsbränder, inklusive aktiv branddetektering med hjälp av ett multikriterietillvägagångssätt och detektering av bränt område med DL-modeller. För aktiv branddetektering utvecklas en multikriteriemetod baserad på reflektionen av B4, B11 och B12 i Stentinel-2 MSI data för flera representativa brandbenägna biom för att få fram otvetydiga pixlar för aktiv brand. De adaptiva tröskelvärdena för varje biom bestäms statistiskt från 11 miljoner Sentinel-2 observationsprover som förvärvats under sommaren (juni 2019 till september 2019) i 14 regioner eller länder. Det primära kriteriet härleds från 3-sigma-prediktionsintervallet för OLS-regression av observationsprover för varje biom. Mer specifika kriterier baserade på B11 och B12 införs vidare för att minska utelämningsfel (OE) och kommissionsfel (CE). Det multikriteriella tillvägagångssättet visar sig vara effektivt när det gäller upptäckt av svala pyrande bränder i undersökningsområden med tropiska och subtropiska gräsmarker, savanner och buskmarker med hjälp av det primära kriteriet. Samtidigt kan ytterligare kriterier som tröskelvärden för reflektionen av B11 och B12 effektivt minska det fel som orsakas av extremt ljusa lågor runt de heta kärnorna i testområden med skogar, skogsmarker och buskage i Medelhavsområdet. Det andra kriteriet som bygger på förhållandet mellan B12 och B11:s reflektionsgrad undviker också effekterna av CE som orsakas av heta markpixlar i områden med tropiska och subtropiska fuktiga lövskogar. Sammantaget visar valideringsresultatet för testområden att CE och OE kan hållas på en låg nivå (0,14 och 0,04) som en godtagbar kompromiss. Algoritmen med flera kriterier lämpar sig för snabb aktiv branddetektering baserad på unika tidsmässiga bilder utan krav på tidsmässiga data. Multispektrala data med medelhög upplösning kan användas som ett kompletterande val till bilder med kursupplösning på grund av deras förmåga att upptäcka små brinnande områden och att upptäcka aktiva bränder mer exakt. När det gäller kartläggning av brända områden syftar denna avhandling till att förklara hur djupa DL-modeller kan användas för att automatiskt kartlägga brända områden från multispektrala bilder i ett tidsintervall. Olika algoritmer för upptäckt av brända områden har utvecklats med hjälp av Sentinel-2 och/eller Landsat-data, men de flesta av studierna kräver att man har en förebränning. bild före branden, täta tidsseriedata eller ett empiriskt tröskelvärde. I den här avhandlingen tillämpas flera arkitekturer för semantiska segmenteringsnätverk, dvs. U-Net, HRNet, Fast- SCNN och DeepLabv3+, på Sentinel- 2 bilder och Landsat-8 bilder över tre testplatser i två lokala klimatzoner. Dessutom används tre populära algoritmer för maskininlärning (ML) (Light- GBM, KNN och slumpmässiga skogar) och NBR-tröskelvärden (empiriska och OTSU-baserade) i samma undersökningsområden för jämförelse. Valideringsresultaten visar att DL-algoritmerna överträffar maskininlärningsmetoderna (ML) i två av de tre fallen med kompakta brända ärr, medan ML-metoderna verkar vara mer lämpliga för kartläggning av spridda ärr i boreala skogar. Med hjälp av Sentinel-2 bilder uppvisar U-Net och HRNet jämförelsevis identiska prestanda med högre kappa (omkring 0,9) i en heterogen brandplats i Medelhavet i Grekland; Fast-SCNN presterar bättre än andra med kappa över 0,79 i en kompakt boreal skogsbrand med varierande brännskadegrad i Sverige. Vid direkt överföring av de tränade modellerna till motsvarande Landsat-8-data dominerar HRNet dessutom på de tre testplatserna bland DL-modellerna och kan bevara den höga noggrannheten. Resultaten visade att DL-modeller kan utnyttja kontextuell information fullt ut och fånga rumsliga detaljer i flera skalor från brandkänsliga spektralband för att kartlägga brända områden. Med den unika tidsmässiga bilden har DL-baserade metoder potential att användas för nästa jordobservationssatellit med databehandling ombord och begränsad lagring av tidigare scener. I den framtida studien kommer DL-modeller att undersökas för att upptäcka aktiva bränder från fjärranalysdata med flera upplösningar. Det befintliga problemet med obalanserade märkta data kan lösas med hjälp av en avancerad DL-arkitektur, lämplig konfiguration av träningsdatasetet och förbättrad förlustfunktion. För att ytterligare utforska de skador som orsakas av skogsbränder kommer det framtida arbetet att fokusera på bedömningen av brännskadornas allvarlighetsgrad baserat på DL-modeller genom semantisk segmentering av flera klasser. Dessutom kan översättningen mellan optiska bilder och SAR-bilder baserad på en GAN-modell (Generative Adversarial Network) undersökas för att förbättra kartläggningen av brända områden under olika väderförhållanden.

QC 20210525

The core function of the basal ganglia is action selection, the process of choosing between mutually exclusive actions. Under baseline or default conditions, the basal ganglia suppress movement and prevent more than one movement from occurring simultaneously. The importance of chunking and operational learning is explored through exemplary typing tasks. Pathways through the basal ganglia employ the same input and output ports. Inputs far outnumber outputs from the basal ganglia. Subcortical loops through the basal ganglia are more effective than are cortical loops. The functions of the hyperdirect, direct and indirect pathways to motor control in the skeletomotor loop are detailed. Hemiballismus, Parkinson’s disease, and Huntington’s disease are key basal ganglia disorders. The use of deep brain stimulation (DBS) of the subthalamic nucleus as a treatment for Parkinson’s disease is discussed. Finally, additional basal ganglia loops such as the oculomotor loop are introduced.

Chapter 2 emphasizes the importance of the monastic tenet of stability, showing the methods by which teachers and communities help ground newcomers in their intentions to follow demanding contemplative Christian alternatives while nevertheless allowing for ambiguity and open-mindedness toward people who follow other lifeways. Rather than depending on unreliable belief and emotion, neophytes learn to keep intentions and practices as a way of working toward “contemplative transformation,” a kind of religious conversion. The difficulties they have in learning practices and principles, especially discipline, humility, and detachment, reveal some deep-seated American cultural motifs of self-identity, self-achievement, and acquisition. Ethnographic examples illustrate the critical role of teachers in stabilizing neophytes as they struggle to learn the paradox of focusing their lives while retaining a non-judgmental, pluralistic outlook. Some key practices include keeping a rule of life, practicing silence and Centering Prayer, maintaining a sense of humor, and serving others through social action.

This book provides a historical account of the development and implications of early modern probabilism. First elaborated in the sixteenth century, probabilism represented a significant and controversial novelty in Catholic moral theology. Against a deep-seated tradition defending the strict application of moral rules, probabilist theologians maintained that in situations of uncertainty, the agent can legitimately follow any course of action supported by a probable opinion, no matter how disputable. By the second half of the seventeenth century, and thanks in part to Pascal’s influential antiprobabilist stances, probabilism had become inextricably linked to the Society of Jesus and to a lax and excessively forgiving moral system. To this day, most historians either ignore probabilism, or they associate it with moral duplicity and intellectual and cultural decadence. By contrast, this book argues that probabilism was instrumental for addressing the challenges created by a geographically and intellectually expanding world. Early modern probabilist theologians saw that these challenges provoked an exponential growth of uncertainties, doubts, and dilemmas of conscience, and they realized that traditional theology was not equipped to deal with them. Therefore, they used probabilism to integrate changes and novelties within the post-Reformation Catholic theological and intellectual system. Seen in this light, probabilism represented the result of their attempts to appreciate, come to terms with, and manage uncertainty. Uncertainty continues to play a central role even today. Thus, learning how early modern probabilists engaged with uncertainty might be useful for us as we try to cope with our own moral and epistemological doubts.

TOWARDS THE NEW LIFE Theology and Importance of Christian Initiation for the Life of Faith The book is in equal parts a presentation and an invitation. The subject matter of both is the mystagogical initiation leading to the personal encounter with God and eventually to the union within the Church in Christ, which happens initially and particualry in the sacramental liturgy. Mystagogy was the essential experience of life in the early Church and now is being so intensely discussed and postulated by the ecclesial Magisterium and through the teaching of the recent popes and synods. Within the ten chapters of this book the reader proceeds through the aspects strictly associated with Christian initiation, noticeable in catechumenate and suggestive for further Christian life. It is not surprising then, that the study begins with answering the question about the sense of dealing with catechumenate at all. The response developed in the first chapter covers four key points: the contemporary state of our faith, the need for dialogue in evangelization, the importance of liturgy in the renewal of faith and the obvious requirement of follo- wing the Church’s Magisterium, quite explicit in the subject undertaken within this book. The introductory chapter is meant to evoke interest in catechumenate as such and encourage comprehension of its essence, in order to keep it in mind while planning contemporary evangelization. For doing this with success and avoiding pastoral archeology, we need a competent insight into the main message and goal of Christian initiation. Catechumenate is the first and most venerable model of formation and growth in faith and therefore worth knowing. The second chapter tries to cope with the reasons and ways of the present return to the sources of catechumenate with respect to Christian initiation understood to be the building of the relationship with God. The example of catechumenate helps us to discover, how to learn wisely from the history. This would definitely mean to keep the structure and liturgy of catechumenate as a vehicle of God’s message, which must be interpreted and adapted always anew and with careful and intelligent consideration of the historical flavour on particular stages within the history of salvation and cultural conditions of the recipients. For that reason we refer to the Biblical resources and to the historical examples of catechumenate including its flourishing and declining periods, after which we are slowly approaching the present reinterpretation of the catechumenal process enhanced by the official teaching of the Church. As the result of the latter, particularly owing to the Vatican Council II, we are now dealing with the renewed liturgy of baptism displayed in two liturgical books: The Rite of Baptism for Children and the Rite of Christian Initiation of Adults (RCIA). This version for adults is the subjectmatter of the whole chapter, in which a reader can find theological analyses of the particular rites as well as numerous indications for improving one’s life with Christ in the Church. You can find interesting associations among the rites of initiation themselves and astounding coherence between those rites and the sacraments of the Eucharist, penance and other sacraments, which simply means the ordinary life of faith. Deep and convincing theology of the process of initiation proves the inspiring spiritual power of the initial and constitutive sacraments of baptism and confirmation, which may seem attractive not only for catechumens but also for the faithful baptized in their infancy, and even more, since they might have not yet had a chance to see what a plausible treasure they have been conveying in their baptismal personality. How much challenge for further and constant realization in life may offer these introductory events of Christian initiation, yet not sufficiently appreciated by those who have already been baptized and confirmed! We all should submit to permanent re-evangelization according to this primary pattern, which always remains essential and fundamental. Very typical and very post-conciliar approach to Christian formation appears in the communal dimension, which guards and guarantees the ecclesial profile of initiation and prepares a person to be a living member of the Church. The sixth chapter of the book is dealing with ecclesial issues in liturgy. They refer to comprehending the word of God, especially in the context of liturgy, which brings about a peculiar theological sense to it and giving a special character to proclaiming the Gospel, which the Pope Francis calls “liturgical proclamation”. The ecclesial premises influence the responsibility for the fact of accompanying the candidates, who aim at becoming Christ’s disciples. As the Church is teaching also in the theological and pastoral introduction to the RCIA, this is the duty of all Christians, which means: priests, religious and the lay, because the Church is one organism in whose womb the new members are conceived and raised. As this fact is strongly claimed by the Church the method of initiation arises to great importance. The seventh chapter is dedicated to the analysis of the catechumenal method stemming from Christ’s pedagogy and His mystery of Incarnation introducing a very important issue of implementing the Divine into the human. The chapter concerning this method opens a more practical part of the book. The crucial message of it is to make mystagogy a natural and obvious method which is the way of building bonds with Christ in the community of the people who already have these bonds and who are eager to tighten them and are aware of the beauty and necessity of closeness with Christ. Christian initiation is the process of entering the Kingdom of God and meeting Christ up to the union with Him – not so much learning dogmas and moral requirements. This is a special time when candidates-catechumens-elected mature in love and in their attitude to Christ and people, which results in prayer and new way of life. As in the past catechumenate nowadays inspires the faithful in their imagination of love and mercy as well as reminds us about various important details of the paschal way of life, which constitute our baptismal vocation, but may be forgotten and now with the help of catechumenate can be recognized anew, while accompanying adults on their catechumenal way. The book is meant for those who are already involved in catechumenal process and are responsible for the rites and formation as well as for those who are interested in what the Church is offering to all who consciously decide to know and follow Christ. You can learn from this book, what is the nature and specificity of the method suggested by the Rite itself for guiding people to God the Saviour and to the community of His people. The aim of the study is to present the universal way of evangelization, which was suggested and revealed by God in His pedagogy, particularly through Jesus Christ and smoothly adopted by the early Church. This way, which can be called a method, is so complete, substantial and clear that it deserves rediscovery, description and promotion, which has already started in the Church’s teaching by making direct references to such categories as: initiation, catechumenate, liturgical formation, the rereading the Mystery of Christ, the living participation in the Mystery and faith nourished by the Mystery. The most engaging point with Christian initiation is the fact, that this seems to be the most effective way of reviving the parish, taking place on the solid and safe ground of liturgy with the most convincing and objective fact that is our baptism and our new identity born in baptismal regenerating bath. On the grounds of our personal relationship with God and our Christian vocation we can become active apostles of Christ. Evangelization begins with ourselves and in our hearts. Thinking about the Church’s mission, we should have in mind our personal mission within the Church and we should refer to it’s roots – first to our immersion into Christ’s death and resurrection and to the anointment with the Holy Spirit. In this Spirit we have all been sent to follow Christ wherever He goes, not necessarily where we would like to direct our steps, but He would. Let us cling to Him and follow Him! Together with the constantly transforming and growing Church! Towards the new life!

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating. Most existing works are based on shallow linear models by assuming that each sample can be well approximated by the span (i.e., the set of all linear combinations) of certain selected samples, and then take these selected samples as representative ones to label. However, in practice, the data do not necessarily conform to linear models, and how to model nonlinearity of data often becomes the key point to success. In this paper, we present a novel Deep neural network framework for Unsupervised Active Learning, called DUAL. DUAL can explicitly learn a nonlinear embedding to map each input into a latent space through an encoder-decoder architecture, and introduce a selection block to select representative samples in the the learnt latent space. In the selection block, DUAL considers to simultaneously preserve the whole input patterns as well as the cluster structure of data. Extensive experiments are performed on six publicly available datasets, and experimental results clearly demonstrate the efficacy of our method, compared with state-of-the-arts.

Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is selected by grid search on a held-out validation set. This is strictly inapplicable to active learning. Within the standardized workflow, the acquisition function is chosen among available heuristics a priori, and its success is observed only after the labeling budget is already exhausted. More importantly, none of the earlier studies report a unique consistently successful acquisition heuristic to the extent to stand out as the unique best choice. We present a method to break this vicious circle by defining the acquisition function as a learning predictor and training it by reinforcement feedback collected from each labeling round. As active learning is a scarce data regime, we bootstrap from a well-known heuristic that filters the bulk of data points on which all heuristics would agree, and learn a policy to warp the top portion of this ranking in the most beneficial way for the character of a specific data distribution. Our system consists of a Bayesian neural net, the predictor, a bootstrap acquisition function, a probabilistic state definition, and another Bayesian policy network that can effectively incorporate this input distribution. We observe on three benchmark data sets that our method always manages to either invent a new superior acquisition function or to adapt itself to the a priori unknown best performing heuristic for each specific data set.

Disruptive innovators take advantage of unique opportunities. Prior to COVID-19 progress in Latin America and the Caribbean for integrating technology, learning, and system change has been exceedingly slow. In this paper we first offer a general framework for transforming education. The framework focuses on the provision of technology, innovative ideas in learning and well-being, and what we call systemness which are favorable change factors at the local, middle/regional, and policy levels. We then take up the matter of system reform in Latin America and the Caribbean noting problems and potential. Then, we turn to a specific model in system change that we have developed called New Pedagogies for Deep Learning, a model developed in partnerships with groups of schools in ten countries since 2014. The model consists of three main components: 6 Global Competences (character, citizenship, collaboration, communication, creativity, and critical thinking), 4 learning elements (pedagogy, learning partnerships, learning environments, leveraging digital), and three system conditions (school culture, district/regional culture, and system policy). We offer a case study of relative success based on Uruguay with whom we have been working since 2014. Finally, we identify steps and recommendations for next steps in Latin America for taking action on system reform in the next perioda time that we consider critical for taking advantage of the current pandemic disruption. The next few years will be crucial for either attaining positive breakthroughs or slipping backwards into a reinforced status quo.