检索结果-内蒙古大学图书馆

Locally linear embedding and its variants: Tutorial and survey

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ghojogh, Benyamin Ghodsi, Ali Karray, Fakhri Crowley, Mark Department of Electrical and Computer Engineering Machine Learning Laboratory University of Waterloo WaterlooON Canada Department of Statistics and Actuarial Science & David R. Cheriton School of Computer Science Data Analytics Laboratory University of Waterloo WaterlooON Canada Department of Electrical and Computer Engineering Centre for Pattern Analysis and Machine Intelligence University of Waterloo WaterlooON Canada

This is a tutorial and survey paper for Locally Linear Embedding (LLE) and its variants. The idea of LLE is fitting the local structure of manifold in the embedding space. In this paper, we first cover LLE, kernel LLE, inverse LLE, and feature fusion with LLE. Then, we cover out-of-sample embedding using linear reconstruction, eigenfunctions, and kernel mapping. Incremental LLE is explained for embedding streaming data. Landmark LLE methods using the Nystrom approximation and locally linear landmarks are explained for big data embedding. We introduce the methods for parameter selection of number of neighbors using residual variance, Procrustes statistics, preservation neighborhood error, and local neighborhood selection. Afterwards, Supervised LLE (SLLE), enhanced SLLE, SLLE projection, probabilistic SLLE, supervised guided LLE (using Hilbert-Schmidt independence criterion), and semi-supervised LLE are explained for supervised and semi-supervised embedding. Robust LLE methods using least squares problem and penalty functions are also introduced for embedding in the presence of outliers and noise. Then, we introduce fusion of LLE with other manifold learning methods including Isomap (i.e., ISOLLE), principal component analysis, Fisher discriminant analysis, discriminant LLE, and Isotop. Finally, we explain weighted LLE in which the distances, reconstruction weights, or the embeddings are adjusted for better embedding;we cover weighted LLE for deformed distributed data, weighted LLE using probability of occurrence, SLLE by adjusting weights, modified LLE, and iterative LLE. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

Inconsistency Distillation For Consistency:Enhancing Multi-View Clustering via Mutual Contrastive Teacher-Student Leaning

学校读者我要写书评

暂无评论

Inconsistency Distillation For Consistency:Enhancing Multi-V...

IEEE International Conference on data Mining (ICDM)

作者： Dunqiang Liu Shu-Juan Peng Xin Liu Lei Zhu Zhen Cui Taihao Li Dept. of Comput. Sci. & Fujian Key Lab. of Big Data Intelligence and Security Huaqiao University Xiamen China Zhejiang Lab Hangzhou China Xiamen Key Lab. of Computer Vision and Pattern Recognition Huaqiao University Xiamen China Key Lab. of Computer Vision and Machine Learning (Huaqiao University) Fujian Province University Xiamen China School of Information Sci. and Eng. Shandong Normal University Jinan China School of Computer Sci. and Eng. Nanjing University of Science and Technology Nanjing China

Multi-view clustering has attracted more attention recently since many real-world data are comprised of different representations or views. Recent multi-view clustering works mainly exploit the instance consistency to obtain the shared representations across different views, and apply a single-view clustering method to perform data partitions. However, these existing methods often ignore the inconsistency of instance associations within the views, which may enlarge the intra-class diversity among the views and therefore degrade the clustering performance. To address this issue, this paper proposes an efficient mutual contrastive teacher-student leaning (MC-TSL) model to enhance the multi-view clustering, which is the first attempt to study the inconsistency distillation for consistency learning. First, the proposed MC-TSL approach exploits a view-specific encoder with two heads, an instance encoding head and a semantic distillation head, respectively, for capturing the consistent and discriminative feature representations. To be specific, the former head exploits a cross-view contrastive learning method to obtain a redundancy-free consistent representation at the instance level, while the latter head designs a mutual teacher-student learning module to capture the intra-view information at semantic level. By training these two heads in an end-to-end manner, the discriminative multi-view embeddings are efficiently obtained and refined by minimizing the weighted sum of the reconstruction loss, contrastive loss and contrast distillation loss. Extensive experiments verify the superiorities of the proposed MC-TSL framework and show its competitive clustering performances.

关键词： Training learning systems Clustering methods Semantics Encoding data mining

Evaluating deep transfer learning for whole-brain cognitive decoding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Thomas, Armin W. Lindenberger, Ulman Samek, Wojciech Müller, Klaus-Robert Machine Learning Group Dept. of Computer Science and Electrical Engineering Technische Universität Berlin Berlin Germany Center for Lifespan Psychology Max Planck Institute for Human Development Berlin Germany Stanford Data Science Stanford University StanfordCA United States Dept. of Psychology Stanford University StanfordCA United States Max Planck UCL Centre for Computational Psychiatry and Ageing Research Berlin Germany Dept. of Artificial Intelligence Fraunhofer Heinrich Hertz Institute Berlin Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany Dept. of Artificial Intelligence Korea University Seoul Korea Republic of Max Planck Institute for Informatics Saarbrücken Germany

Research in many fields has shown that transfer learning (TL) is well-suited to improve the performance of deep learning (DL) models in datasets with small numbers of samples. This empirical success has triggered interest in the application of TL to cognitive decoding analyses with functional neuroimaging data. Here, we systematically evaluate TL for the application of DL models to the decoding of cognitive states (e.g., viewing images of faces or houses) from whole-brain functional Magnetic Resonance Imaging (fMRI) data. We first pre-train two DL architectures on a large, public fMRI dataset and subsequently evaluate their performance in an independent experimental task and a fully independent dataset. The pre-trained models consistently achieve higher decoding accuracies and generally require less training time and data than model variants that were not pre-trained, clearly underlining the benefits of pre-training. We demonstrate that these benefits arise from the ability of the pre-trained models to reuse many of their learned features when training with new data, providing deeper insights into the mechanisms giving rise to the benefits of pre-training. Yet, we also surface nuanced challenges for whole-brain cognitive decoding with DL models when interpreting the decoding decisions of the pre-trained models, as these have learned to utilize the fMRI data in unforeseen and counterintuitive ways to identify individual cognitive states. © 2021, CC BY.

关键词： Decoding

Analysis Of A Zipline Robotic System To Assist Astronauts On Lunar And Martian Terrains 73

学校读者我要写书评

暂无评论

Analysis Of A Zipline Robotic System To Assist Astronauts On...

73rd International Astronautical Congress, IAC 2022

作者： Kadagadakai, Vishnurat Thuluva, Sushmith Kodukula, Ananya Bharadwaj, Vyoma Jain, Alankriti Rao, Bhavana B. Pulicallu, Greeshmanth Rai, Riddhi Shukla, Aayush Mitra, Ruhi Nanditha Prabhu, M. Kamath, Satwik Preetham, M.P. Department of Electronics & Telecommunication Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Electrical and Computer Engineering Carnegie Mellon University 5000 Forbes Ave PittsburghPA15213 United States Department of Computer Science & Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Mechanical Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Artificial Intelligence & Data Science Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Artificial Intelligence & Machine Learning Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Information Science & Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Electronics & Communication Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India

In the realm of drones and probes, this paper proposes a subsequent derivative idea of ziplining automated mobile systems to assist astronauts on Lunar and Martian surfaces. Although the conventional human-like robotic systems alleviate many challenges to astronauts on the moon and the mars, one particular challenge of reaching farther on land is left to the technology of drones. Drones however are more efficient in overviewing the area and are less effective in transporting samples or astronauts to the target. This paper discusses an idea of a ziplining robotic system that can reach farther places from the base camp in a secure and safe way. The system comprises multiple support poles, a subsystem of ziplining and a mobility subsystem to traverse the contents from point to point. This paper describes the overall design of the robotic system, its operations and possible advancements for the future scope. The future applications of such an idea involves the support for constructing a settlement for our Martian outposts. The paper explores these domains of applications and the effectiveness of such a mobility system in various situations. The paper investigates the proposed design on Lunar and Martian surfaces but can be optimised for other planetary bodies as well. © 2022 International Astronautical Federation, IAF. All rights reserved.

关键词： Drones

A Strategic Approach To Tackle Interplanetary Communication Delay: Exploiting Artificial Intelligence Solutions For Future Space Exploration 73

学校读者我要写书评

暂无评论

A Strategic Approach To Tackle Interplanetary Communication ...

73rd International Astronautical Congress, IAC 2022

作者： Rai, Riddhi Thuluva, Sushmith Kodukula, Ananya Bharadwaj, Vyoma Jain, Alankriti Shadaksharaiah, Anushree Maligehalli Pulicallu, Greeshmanth Kadagadakai, Vishnurat Shukla, Aayush Mitra, Ruhi Nanditha Prabhu, M. Preetham, M.P. Department of Artificial Intelligence & Data Science Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Electrical and Computer Engineering Carnegie Mellon University 5000 Forbes Ave PittsburghPA15213 United States Department of Computer Science & Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Electronics & Telecommunication Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Electronics & Instrumentation Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Mechanical Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Artificial Intelligence & Machine Learning Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Information Science & Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India

Despite the extreme measures in any interplanetary mission, a probe is inevitably prone to a handful of unexpected errors. Concerning this, an exceptional challenge in every interplanetary endeavour is the inescapable communication gap (delay) resulting from the various factors. Although the gap is in the range of few minutes to seconds, the actions performed by the probe during critical events creates the necessary to establish a continuous and real time communication with the mission control. Thinking long term on manned missions to Mars and beyond, escalates the concern *** currently tackling such communication issues faced when a satellite communicates with earth is of high *** current paper proposes an alternate strategy to tackle this subject. With recent advancements in the development of Artificial Intelligence (AI), state-of-the art algorithms,neural networks, and reinforcement based models, it can be so optimized for applications suitable to meet the needs of satellite communication issues. In the light of which, the paper investigates the design of a monitoring satellite. This monitoring satellite is trained with the data and a developed deep learning algorithm/machine learning model is employed by the satellite to make future decisions. Hence using the current knowledge and data we have regarding the communication issues faced while establishing a link with earth, we can train the data models present in the satellite to make the communication with earth more *** the results we gain from this can be later transferred to tackle interplanetary communication *** in the future,we can transfer this knowledge to a a probe that can help tackle interplanetary communication. Copyright © 2022 by the International Astronautical Federation (IAF). All rights reserved.

关键词： Satellites

An Innovative Design Of A Reusable Constellation Of CubeSats For Space Debris Removal 73

学校读者我要写书评

暂无评论

An Innovative Design Of A Reusable Constellation Of CubeSats...

73rd International Astronautical Congress, IAC 2022

作者： Shukla, Aayush Thuluva, Sushmith Kodukula, Ananya Bharadwaj, Vyoma Jain, Alankriti Shadaksharaiah, Anushree Maligehalli Pulicallu, Greeshmanth Kadagadakai, Vishnurat Rai, Riddhi Mitra, Ruhi Prabhu, M. Nanditha Department of Artificial Intelligence & Machine Learning Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Electrical and Computer Engineering Carnegie Mellon University 5000 Forbes Ave PittsburghPA15213 United States Department of Computer Science & Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Electronics & Telecommunication Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Electronics & Instrumentation Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Mechanical Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Artificial Intelligence & Data Science Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India Department of Information Science & Engineering Ramaiah Institute of Technology MSRIT Post M S Ramaiah Nagar MSR Nagar Karnataka Bengaluru560054 India

Space debris is one significant setback in our attempt to explore space and enhance satellite technology. Eradicating this upshot is eminent to our future missions and a safe environment for our planet. The scale of the space junk in the low earth orbit is around few hundreds of thousands and more, sizing from 10s of centimeters in diameter and lower. Although it is inevitable for the space debris to reenter the atmosphere naturally, it is a matter of years and hence the rate is too slow. With advances in the CubeSat technology, a variety of designs are possible for CubeSat systems to function as per the mission requirements. The current paper hence nominates an idea to remove some of the inoperative satellites and it's corresponding components with the help of a constellation of CubeSats that are equipped with distributed actuators for propulsion. The CubeSats are so designed to function as a propulsive device alone with minimal subsystem requirements. The constellation is contained in a cuboidal station with CubeSats docked on all the lateral sides. Once a target body is locked and intended to be removed, the constellation releases one or more CubeSats en route to the target body. Once at site, the CubeSats attach themselves to the target and propel the body to reenter the atmosphere. This constellation station is so designed to be compatible for reusability and the maintenance of such a design is discussed in the paper. The entire approach is thoroughly analyzed investigating multiple designs for the CubeSats. An additional benefit of the proposed idea is to ensure an immediate solution for deorbiting any critically unstable debris in the future in an event of emergency. Copyright © 2022 by the International Astronautical Federation (IAF). All rights reserved.

关键词： Space debris

learning Domain Invariant Representations by Joint Wasserstein Distance Minimization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Andéol, Léo Kawakami, Yusei Wada, Yuichiro Kanamori, Takafumi Müller, Klaus-Robert Montavon, Grégoire Machine Learning group Technische Universität Berlin Berlin10587 Germany Tokyo Institute of Technology Tokyo Japan Berlin Institute for the Foundations of Learning and Data – BIFOLD Berlin10587 Germany Fujitsu Laboratories Ltd. Japan RIKEN AIP Japan Max Planck Institute for Informatics Stuhlsatzenhausweg 4 Saarbrücken66123 Germany Department of Artificial Intelligence Korea University Seoul136-713 Korea Republic of Google Deepmind Berlin Germany Department of Mathematics and Computer Science Freie Universität Berlin Berlin14195 Germany

Domain shifts in the training data are common in practical applications of machine learning;they occur for instance when the data is coming from different sources. Ideally, a ML model should work well independently of these shifts, for example, by learning a domain-invariant representation. However, common ML losses do not give strong guarantees on how consistently the ML model performs for different domains, in particular, whether the model performs well on a domain at the expense of its performance on another domain. In this paper, we build new theoretical foundations for this problem, by contributing a set of mathematical relations between classical losses for supervised ML and the Wasserstein distance in joint space (i.e. representation and output space). We show that classification or regression losses, when combined with a GAN-type discriminator between domains, form an upper-bound to the true Wasserstein distance between domains. This implies a more invariant representation and also more stable prediction performance across domains. Theoretical results are corroborated empirically on several image datasets. Our proposed approach systematically produces the highest minimum classification accuracy across domains, and the most invariant representation. Copyright © 2021, The Authors. All rights reserved.

关键词： machine learning

Land instability Compounds the risk of sea level rise in Alexandria, Egypt

学校读者我要写书评

暂无评论

International Journal of Applied Earth Observation and Geoinformation 2025年 141卷

作者： Thomas, Rejoice Zouriq, Sara Fazli, Shahryar Fawzy, Amr Todorov, Nikolay Grisel Maharjan, Surendra Li, Wenzhao Linstead, Erik Struppa, Daniele El-Askary, Hesham Earth Systems Science and Data Solutions Lab Chapman University Orange 92866 CA United States Schmid College of Science and Technology Chapman University Orange 92866 CA United States Ministry of Water Resources and Irrigation Cairo Egypt Machine Learning and Assistive Technology Lab (MLAT) Chapman University Orange 92866 CA United States Fowler School of Engineering Chapman University Orange 92866 CA United States Department of Environmental Sciences Faculty of Science Alexandria University Moharem Bek Alexandria 21522 Egypt

The coastal region of Alexandria Governorate in Egypt holds significant strategic importance for trade while being susceptible to extreme weather events. It confronts a dual challenge of the rising sea levels and, as found in this study, land instability. While much attention has been rightly directed towards sea level rise (SLR), the stability of the land warrants equal consideration. Here, a comprehensive analysis of land stability is conducted in Alexandria by measuring Line of Sight (LOS) displacements and assessing their topographical, hydrological, and coastal impacts. Persistent Scatterer Interferometry technique is used to measure the LOS displacements in association with land cover classification and elevation data. Moreover, in the absence of a recent, openly accessible Digital Elevation Model (DEM) with satisfactory resolution, we developed a novel approach to update DEM using the Small Baseline Subset method. This approach enabled us to generate a projected DEM for the year 2040, facilitating the creation of a stream network based on this “future DEM”. Our observations revealed displacements ranging from −14.0 to 6.7 mm/year, predominantly occurring in low-lying and built-up areas, suggesting anthropogenic activities as a likely cause. The current and future stream networks show stream shifting and widening. Stream shifting indicates dynamic changes in topography and hydrological conditions, while stream widening suggests alterations in the hydrological network due to increased urban runoff or changes in the natural watershed. Furthermore, we found that sea surface temperature and SLR are projected to increase until the end of the century in the Mediterranean Sea near Alexandria. This escalation raises the likelihood of intensified tropical-like hurricane events in the region, commonly referred to as “medicanes”. The importance of this research is in offering a framework for comprehensive land stability assessments, along with demonstrating the scalabili

关键词： Digital Elevation Model Medicanes Persistent Scatterer Interferometry Sea Level Rise Sea Surface Temperature Small Baseline Subset

An improved approach for estimating social POI boundaries with textual attributes on social media

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tran, Cong Vu, Dung D. Shin, Won-Yong Department of Computer Science and Engineering Dankook University Yongin16890 Korea Republic of Machine Learning R&D Korbit AI MontrealQCH2T 2A3 Canada Machine Intelligence & Data Science Laboratory Yonsei University Seoul03722 Korea Republic of Yonsei University Seoul03722 Korea Republic of

It has been insufficiently explored how to perform density-based clustering by exploiting textual attributes on social media. In this paper, we aim at discovering a social point-of-interest (POI) boundary, formed as a convex polygon. More specifically, we present a new approach and algorithm, built upon our earlier work on social POI boundary estimation (SoBEst). This SoBEst approach takes into account both relevant and irrelevant records within a geographic area, where relevant records contain a POI name or its variations in their text field. Our study is motivated by the following empirical observation: a fixed representative coordinate of each POI that SoBEst basically assumes may be far away from the centroid of the estimated social POI boundary for certain POIs. Thus, using SoBEst in such cases may possibly result in unsatisfactory performance on the boundary estimation quality (BEQ), which is expressed as a function of the F-measure. To solve this problem, we formulate a joint optimization problem of simultaneously finding the radius of a circle and the POI’s representative coordinate c by allowing to update c. Subsequently, we design an iterative SoBEst (I-SoBEst) algorithm, which enables us to achieve a higher degree of BEQ for some POIs. The computational complexity of the proposed I-SoBEst algorithm is shown to scale linearly with the number of records. We demonstrate the superiority of our algorithm over competing clustering methods including the original SoBEst. © 2020, CC BY.

关键词： Social networking (online)