616 research outputs found
Jie gou xing tu you hua de wu cha jie xian: li lun ji ying yong
No full textZhou, Zirui.Thesis Ph.D. Chinese University of Hong Kong 2015.Includes bibliographical references (leaves 94-102).Abstracts also in Chinese.Title from PDF title page (viewed on 02, November, 2016).Zhou, Zirui
Inference of Tree-type Event Spreading Pattern from Time-series Data
No full textChen, Zirui.Thesis M.Phil. Chinese University of Hong Kong 2016.Includes bibliographical references (leaves ).Abstracts also in Chinese.Title from PDF title page (viewed on …)
An Ultrafast (< 200 ns) Sparse Solution Solver made by HfWOx/VOy Threshold Tunable Neurons
No full textGraph Bayesian Optimization for Multiplex Influence Maximization
No full textInfluence maximization (IM) is the problem of identifying a limited number of initial influential users within a social network to maximize the number of influenced users. However, previous research has mostly focused on individual information propagation, neglecting the simultaneous and interactive dissemination of multiple information items. In reality, when users encounter a piece of information, such as a smartphone product, they often associate it with related products in their minds, such as earphones or computers from the same brand. Additionally, information platforms frequently recommend related content to users, amplifying this cascading effect and leading to multiplex influence diffusion.
This paper first formulates the Multiplex Influence Maximization (Multi-IM) problem using multiplex diffusion models with an information association mechanism. In this problem, the seed set is a combination of influential users and information. To effectively manage the combinatorial complexity, we propose Graph Bayesian Optimization for Multi-IM (GBIM). The multiplex diffusion process is thoroughly investigated using a highly effective global kernelized attention message-passing module. This module, in conjunction with Bayesian linear regression (BLR), produces a scalable surrogate model. A data acquisition module incorporating the exploration-exploitation trade-off is developed to optimize the seed set further.
Extensive experiments on synthetic and real-world datasets have proven our proposed framework effective. The code is available at https://github.com/zirui-yuan/GBIM
Graph Bayesian Optimization for Multiplex Influence Maximization
No full textInfluence maximization (IM) is the problem of identifying a limited number of
initial influential users within a social network to maximize the number of
influenced users. However, previous research has mostly focused on individual
information propagation, neglecting the simultaneous and interactive
dissemination of multiple information items. In reality, when users encounter a
piece of information, such as a smartphone product, they often associate it
with related products in their minds, such as earphones or computers from the
same brand. Additionally, information platforms frequently recommend related
content to users, amplifying this cascading effect and leading to multiplex
influence diffusion.
This paper first formulates the Multiplex Influence Maximization (Multi-IM)
problem using multiplex diffusion models with an information association
mechanism. In this problem, the seed set is a combination of influential users
and information. To effectively manage the combinatorial complexity, we propose
Graph Bayesian Optimization for Multi-IM (GBIM). The multiplex diffusion
process is thoroughly investigated using a highly effective global kernelized
attention message-passing module. This module, in conjunction with Bayesian
linear regression (BLR), produces a scalable surrogate model. A data
acquisition module incorporating the exploration-exploitation trade-off is
developed to optimize the seed set further. Extensive experiments on synthetic
and real-world datasets have proven our proposed framework effective. The code
is available at https://github.com/zirui-yuan/GBIM.Comment: Proceedings of the AAAI Conference on Artificial Intelligence, 202
Efficient Deep Learning System in Mobile Computing
No full textIn the past few years, the fast-developing Deep Neural Networks (DNNs) and their broad applications have served as the primary driving horsepower for a new technology wave.However, they are still very computationally intensive for resource-constrained mobile systems. Therefore, a lot of research works were proposed to compress and accelerate DNNs for efficient computation on mobile devices. My research topics during Ph.D. study are mainly focused on building efficient deep learning systems in mobile computing by considering three specific challenges: system deployment, application scenario, and large-scale collaboration. First, from the perspective of single system deployment, in order to adapt DNNs to various hardware constraints on mobile devices, I propose DiReCtX - a dynamic resource-aware DNN model reconfiguration framework. DiReCtX is based on a set of accurate DNN profiling models for different resource consumption and inference accuracy estimation. With manageable consumption/accuracy trade-offs, DiReCtX can reconfigure a DNN model to meet distinct resource constraint types and levels with expected inference performance maintained. Second, from the perspective of the application scenario, I find the input information in most mobile computing scenarios has many redundancies (sparsity patterns) and they are non-structural and randomly located on feature maps with non-identical shapes. Therefore, I develop a novel sparsity computing scheme called FalCon, which can well adapt to the practical sparsity patterns while still maintaining efficient computing. Additionally, a decomposed convolution computing optimization paradigm is proposed to convert the sparsity to practical acceleration. At last, from the perspective of large-scale collaboration, I propose \textit{Helios} --- a heterogeneity-aware FL framework to tackle the straggler issue in the scenario of multi-device collaborative learning. Helios identifies an individual device's heterogeneous training capability and calculates the expected neural network model training volumes on stragglers. For straggling devices, a ``soft-training'' method is proposed to dynamically compress the original identical training model into the expected volume through a rotating neuron training approach. With extensive algorithm analysis and optimization schemes, the stragglers can be accelerated while retaining the convergence for local training as well as federated collaboration. I hope the realization of the projects in this dissertation could contribute to the current research area about efficient deep learning system and motivate more studies on model optimization, collaboration system design, and even compiler-level renovation
Robust 2D and 3D registration with deep neural networks
No full textRecovering 3D geometry is a crucial task in computer vision, essential for accurate world reconstruction and perception. Modern applications in AR, VR, autonomous driving, and medical imaging rely heavily on 3D and 4D reconstruction techniques. This thesis aims to enhance registration methods, which play a key role in reconstruction, by fusing classical multi-view geometry and deep neural networks. We explore this theme in three primary directions, each distinguished by registration dimensionality: 3D–3D, 3D–2D, and 2D–2D.
First, we focus on improving the alignment of 3D point clouds in both rigid and non-rigid scenarios. In non-rigid 3D registration, traditional methods directly optimize a motion field between a source and target surface. This often leads to slow convergence and being trapped in local minima. We introduce a neural network-based scene flow to initialize the optimization, providing a more efficient and robust solution. Additionally, we present a novel surface normal estimation technique that aids both rigid and non-rigid registration. Unlike conventional methods that use a fixed global neighbor parameter, our approach employs a self-attention mechanism to adapt to local geometry variations.
Second, we address the challenge of registering 2D images to 3D Neural Radiance Fields (NeRF) through joint optimization of NeRF and camera parameters. Original NeRF training mandates pre-processed camera parameters, creating a bottleneck in the workflow. Our approach allows for end-to-end camera parameter estimation during NeRF training while reusing the existing photometric loss in NeRF. We further extend this to account for larger camera movements by incorporating a monocular depth prior.
Lastly, we propose a method for interest point discovery, which is beneficial for 2D image registration. Unlike existing interest point identification methods that suffer from significant viewpoint changes and occlusion boundaries, we propose a multi-view interest point discovery approach to address these limitations. Our method is trained in a self-supervised fashion with pure-geometric constraints that encourage point identification repeatability, sparsity, and multi-view consistency.
In summary, this thesis explores the fusion of traditional multi-view geometry concepts with deep learning priors in various registration tasks, including point cloud registration, image-to-NeRF registration, and image-to-image registration
Mitigating Regional Accent Bias in ASR Systems
No full textEnd-to-end Automatic Speech Recognition (ASR) systems improved drastically in recent years and they work extremely well on many large datasets. However, research shows that these models failed to capture the variability in speech production and have biases against the variant caused by the regional accented speech. Moreover, ASR research on regional accents is primarily done in languages used by a large population, like English and Arabic, and the effect of regional accented speech on E2E ASR systems in non-popular languages is still unknown. It is important to know the effect of regional accented speech on E2E ASR systems as it helps researchers to build an inclusive E2E ASR system. In this project, I aim to mitigate the biases against regional accented speech. I select standard speech and regional accented speech from CommonVoice's French and German datasets. I combine the state-of-the-art Conformer Recurrent Neural Network Transducer model with Multi-Domain Adversarial Training (MDAT) to boost the performance of regional accented speech while not hurting the performance of the standard speech. Moreover, since the regional accented speech is typically low-resourced, I study the amount of data required for effective MDAT, as well as the effect of different domain classifiers on the performance of Multi-Domain Adversarial Training. Experimental results show that MDAT can mitigate the biases against regional accented speech in both French and German. The best model in French reduces the bias by around 12% and the best model in German reduces the bias by around 7%. Additionally, MDAT is an effective method for bias mitigation as it can achieve similar performance as the MDAT model trained with the full dataset using only a small amount (e.g. 30 minutes) of untranscribed regional accented speech. Finally, different domain classifier architectures were found to have similar effects on the results of MDAT, thus there is no significant differences among the domain classifier in this project.Electrical Engineering | Embedded System
Research trends on alphavirus receptors: a bibliometric analysis
No full textBackgroundAlphaviruses are a diverse group of pathogens that have garnered considerable attention due to their impact on human health. By investigating alphavirus receptors, researchers can elucidate viral entry mechanisms and gain important clues for the prevention and treatment of viral diseases. This study presents an in-depth analysis of the research progress made in the field of alphavirus receptors through bibliometric analysis.MethodsThis study encompasses various aspects, including historical development, annual publication trends, author and cited-author analysis, institutional affiliations, global distribution of research contributions, reference analysis with strongest citation bursts, keyword analysis, and a detailed exploration of recent discoveries in alphavirus receptor research.ResultsThe results of this bibliometric analysis highlight key milestones in alphavirus receptor research, demonstrating the progression of knowledge in this field over time. Additionally, the analysis reveals current research hotspots and identifies emerging frontiers, which can guide future investigations and inspire novel therapeutic strategies.ConclusionThis study provides an overview of the state of the art in alphavirus receptor research, consolidating the existing knowledge and paving the way for further advancements. By shedding light on the significant developments and emerging areas of interest, this study serves as a valuable resource for researchers, clinicians, and policymakers engaged in combating alphavirus infections and improving public health
Ground-based light curve follow-up validation observations of TESS object of interest TOI 4620.01
No full textThe Transiting Exoplanet Survey Satellite (TESS) is a space telescope for NASA's Explorer program, designed to search for exoplanets using the transit method in an area 400 times larger than that covered by the Kepler mission. During its first two years in orbit, the TESS spacecraft concentrated its gaze on several hundred thousand specially chosen stars, looking for small dips in their light caused by orbiting planets passing between their host star and us. Because of the low spatial resolution of its cameras, TESS is expected to detect several false positives (FPs). It can identify as NEB (Nearby Eclipsing Binary), BEB (Blended Eclipsing Binary) or EB (Eclipsing Binary).We use AIJ(AstroImageJ) to find the TOI 4620.01 and create the lightcurve. We found that the brightness of the planet tends to decrease around the predicted time. After that we identify there is a transit
- …
