In this paper, we present a comprehensive evaluation to establish a robust and efficient framework for Lagrangian-based particle tracing using deep neural networks (DNNs). Han et al. (2021) first proposed a DNN-based approach to learn Lagrangian representations and demonstrated accurate particle tracing for an analytic 2D flow field. In this paper, we extend and build upon this prior work in significant ways. First, we evaluate the performance of DNN models to accurately trace particles in various settings, including 2D and 3D time-varying flow fields, flow fields from multiple applications, flow fields with varying complexity, as well as structured and unstructured input data. Second, we conduct an empirical study to inform best practices with respect to particle tracing model architectures, activation functions, and training data structures. Third, we conduct a comparative evaluation of prior techniques that employ flow maps as input for exploratory flow visualization. Specifically, we compare our extended model against its predecessor by Han et al. (2021), as well as the conventional approach that uses triangulation and Barycentric coordinate interpolation. Finally, we consider the integration and adaptation of our particle tracing model with different viewers. We provide an interactive web-based visualization interface by leveraging the efficiencies of our framework, and perform high-fidelity interactive visualization by integrating it with an OSPRay-based viewer. Overall, our experiments demonstrate that using a trained DNN model to predict new particle trajectories requires a low memory footprint and results in rapid inference. Following best practices for large 3D datasets, our deep learning approach using GPUs for inference is shown to require approximately 46 times less memory while being more than 400 times faster than the conventional methods.
相關內容
In this paper, we present a novel algorithm for classifying ex vivo tissue that comprises multi-channel bioimpedance analysis and a hardware neural network. When implemented in a mixed-signal 180 nm CMOS process, the classifier has an estimated power budget of 39 mW and an area of 30 mm2. This means that the classifier can be integrated into the tip of a surgical margin assessment probe, for in vivo use during radical prostatectomy. We tested our classifier on digital phantoms of prostate tissue and also on an animal model of ex vivo bovine tissue. The classifier achieved an accuracy of 90% on the prostate tissue phantoms, and an accuracy of 84% on the animal model.
In this short paper, we present an innovative approach to limit the required bandwidth when transferring data during in transit analysis. This approach is called hybrid because it combines existing in situ and in transit solutions. It leverages the stable ABI of Catalyst version 2 and the Catalyst-ADIOS2 implementation to seamlessly switch from in situ, in transit and hybrid analysis without modifying the numerical simulation code. The typical use case is to perform data reduction in situ then generate a visualization in transit on the reduced data. This approach makes the numerical simulation workflows very flexible depending on the size of the data, the available computing resources or the analysis type. Our experiment with this hybrid approach, reducing data before sending it, demonstrated large cost reductions for some visualization pipelines compared to in situ and in transit solutions. The implementation is available under an open source permissive license to be usable broadly in any scientific community.
In this study, we introduce MGA-Net, a novel mask-guided attention neural network, which extends the U-net model for precision neonatal brain imaging. MGA-Net is designed to extract the brain from other structures and reconstruct high-quality brain images. The network employs a common encoder and two decoders: one for brain mask extraction and the other for brain region reconstruction. A key feature of MGA-Net is its high-level mask-guided attention module, which leverages features from the brain mask decoder to enhance image reconstruction. To enable the same encoder and decoder to process both MRI and ultrasound (US) images, MGA-Net integrates sinusoidal positional encoding. This encoding assigns distinct positional values to MRI and US images, allowing the model to effectively learn from both modalities. Consequently, features learned from a single modality can aid in learning a modality with less available data, such as US. We extensively validated the proposed MGA-Net on diverse datasets from varied clinical settings and neonatal age groups. The metrics used for assessment included the DICE similarity coefficient, recall, and accuracy for image segmentation; structural similarity for image reconstruction; and root mean squared error for total brain volume estimation from 3D ultrasound images. Our results demonstrate that MGA-Net significantly outperforms traditional methods, offering superior performance in brain extraction and segmentation while achieving high precision in image reconstruction and volumetric analysis. Thus, MGA-Net represents a robust and effective preprocessing tool for MRI and 3D ultrasound images, marking a significant advance in neuroimaging that enhances both research and clinical diagnostics in the neonatal period and beyond.
In this paper, we explore advanced modifications to the Tweedie regression model in order to address its limitations in modeling aggregate claims for various types of insurance such as automobile, health, and liability. Traditional Tweedie models, while effective in capturing the probability and magnitude of claims, usually fall short in accurately representing the large incidence of zero claims. Our recommended approach involves a refined modeling of the zero-claim process, together with the integration of boosting methods in order to help leverage an iterative process to enhance predictive accuracy. Despite the inherent slowdown in learning algorithms due to this iteration, several efficient implementation techniques that also help precise tuning of parameter like XGBoost, LightGBM, and CatBoost have emerged. Nonetheless, we chose to utilize CatBoost, a efficient boosting approach that effectively handles categorical and other special types of data. The core contribution of our paper is the assembly of separate modeling for zero claims and the application of tree-based boosting ensemble methods within a CatBoost framework, assuming that the inflated probability of zero is a function of the mean parameter. The efficacy of our enhanced Tweedie model is demonstrated through the application of an insurance telematics dataset, which presents the additional complexity of compositional feature variables. Our modeling results reveal a marked improvement in model performance, showcasing its potential to deliver more accurate predictions suitable for insurance claim analytics.
In this paper, we propose a method for online domain-incremental learning of acoustic scene classification from a sequence of different locations. Simply training a deep learning model on a sequence of different locations leads to forgetting of previously learned knowledge. In this work, we only correct the statistics of the Batch Normalization layers of a model using a few samples to learn the acoustic scenes from a new location without any excessive training. Experiments are performed on acoustic scenes from 11 different locations, with an initial task containing acoustic scenes from 6 locations and the remaining 5 incremental tasks each representing the acoustic scenes from a different location. The proposed approach outperforms fine-tuning based methods and achieves an average accuracy of 48.8% after learning the last task in sequence without forgetting acoustic scenes from the previously learned locations.
In this paper, we study the problem of detecting machine-generated text when the large language model (LLM) it is possibly derived from is unknown. We do so by apply ensembling methods to the outputs from DetectGPT classifiers (Mitchell et al. 2023), a zero-shot model for machine-generated text detection which is highly accurate when the generative (or base) language model is the same as the discriminative (or scoring) language model. We find that simple summary statistics of DetectGPT sub-model outputs yield an AUROC of 0.73 (relative to 0.61) while retaining its zero-shot nature, and that supervised learning methods sharply boost the accuracy to an AUROC of 0.94 but require a training dataset. This suggests the possibility of further generalisation to create a highly-accurate, model-agnostic machine-generated text detector.
In this paper, we propose a new secure machine learning inference platform assisted by a small dedicated security processor, which will be easier to protect and deploy compared to today's TEEs integrated into high-performance processors. Our platform provides three main advantages over the state-of-the-art: (i) We achieve significant performance improvements compared to state-of-the-art distributed Privacy-Preserving Machine Learning (PPML) protocols, with only a small security processor that is comparable to a discrete security chip such as the Trusted Platform Module (TPM) or on-chip security subsystems in SoCs similar to the Apple enclave processor. In the semi-honest setting with WAN/GPU, our scheme is 4X-63X faster than Falcon (PoPETs'21) and AriaNN (PoPETs'22) and 3.8X-12X more communication efficient. We achieve even higher performance improvements in the malicious setting. (ii) Our platform guarantees security with abort against malicious adversaries under honest majority assumption. (iii) Our technique is not limited by the size of secure memory in a TEE and can support high-capacity modern neural networks like ResNet18 and Transformer. While previous work investigated the use of high-performance TEEs in PPML, this work represents the first to show that even tiny secure hardware with really limited performance can be leveraged to significantly speed-up distributed PPML protocols if the protocol can be carefully designed for lightweight trusted hardware.
In this paper, we present a quantum property testing algorithm for recognizing a context-free language that is a concatenation of two palindromes $L_{REV}$. The query complexity of our algorithm is $O(\frac{1}{\varepsilon}n^{1/3}\log n)$, where $n$ is the length of an input. It is better than the classical complexity that is $\Theta^*(\sqrt{n})$. At the same time, in the general setting, the picture is different a little. Classical query complexity is $\Theta(n)$, and quantum query complexity is $\Theta^*(\sqrt{n})$. So, we obtain polynomial speed-up for both cases (general and property testing).
In this paper, we propose a novel joint deep reinforcement learning (DRL)-based solution to optimize the utility of an uncrewed aerial vehicle (UAV)-assisted communication network. To maximize the number of users served within the constraints of the UAV's limited bandwidth and power resources, we employ deep Q-Networks (DQN) and deep deterministic policy gradient (DDPG) algorithms for optimal resource allocation to ground users with heterogeneous data rate demands. The DQN algorithm dynamically allocates multiple bandwidth resource blocks to different users based on current demand and available resource states. Simultaneously, the DDPG algorithm manages power allocation, continuously adjusting power levels to adapt to varying distances and fading conditions, including Rayleigh fading for non-line-of-sight (NLoS) links and Rician fading for line-of-sight (LoS) links. Our joint DRL-based solution demonstrates an increase of up to 41% in the number of users served compared to scenarios with equal bandwidth and power allocation.
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
In this paper, we introduce a novel theoretical framework for multi-task regression, applying random matrix theory to provide precise performance estimations, under high-dimensional, non-Gaussian data distributions. We formulate a multi-task optimization problem as a regularization technique to enable single-task models to leverage multi-task learning information. We derive a closed-form solution for multi-task optimization in the context of linear models. Our analysis provides valuable insights by linking the multi-task learning performance to various model statistics such as raw data covariances, signal-generating hyperplanes, noise levels, as well as the size and number of datasets. We finally propose a consistent estimation of training and testing errors, thereby offering a robust foundation for hyperparameter optimization in multi-task regression scenarios. Experimental validations on both synthetic and real-world datasets in regression and multivariate time series forecasting demonstrate improvements on univariate models, incorporating our method into the training loss and thus leveraging multivariate information.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191