The present investigation focuses on the application of deep neural network (DNN) models to predict the filtered density function (FDF) of mixture fraction in large eddy simulation (LES) of variable density mixing layers with conserved scalar mixing. A systematic training method is proposed to select the DNN-FDF model training sample size and architecture via learning curves, thereby reducing bias and variance. Two DNN-FDF models are developed: one trained on the FDFs generated from direct numerical simulation (DNS), and another trained with low-fidelity simulations in a zero-dimensional pairwise mixing stirred reactor (PMSR). The accuracy and consistency of both DNN-FDF models are established by comparing their predicted scalar filtered moments with those of conventional LES, in which the transport equations corresponding to these moments are directly solved. Further, DNN-FDF approach is shown to perform better than the widely used $\beta$-FDF method, particularly for multi-modal FDF shapes and higher variances. Additionally, DNN-FDF results are also assessed via comparison with data obtained by DNS and the transported FDF method. The latter involves LES simulations coupled with the Monte Carlo (MC) methods which directly account for the mixture fraction FDF. The DNN-FDF results compare favorably with those of DNS and transported FDF method. Furthermore, DNN-FDF models exhibit good predictive capabilities compared to filtered DNS for filtering of highly non-linear functions, highlighting their potential for applications in turbulent reacting flow simulations. Overall, the DNN-FDF approach offers a more accurate alternative to the conventional presumed FDF method for describing turbulent scalar transport in a cost-effective manner.
相關內容
Bayesian inference for neural networks, or Bayesian deep learning, has the potential to provide well-calibrated predictions with quantified uncertainty and robustness. However, the main hurdle for Bayesian deep learning is its computational complexity due to the high dimensionality of the parameter space. In this work, we propose a novel scheme that addresses this limitation by constructing a low-dimensional subspace of the neural network parameters-referred to as an active subspace-by identifying the parameter directions that have the most significant influence on the output of the neural network. We demonstrate that the significantly reduced active subspace enables effective and scalable Bayesian inference via either Monte Carlo (MC) sampling methods, otherwise computationally intractable, or variational inference. Empirically, our approach provides reliable predictions with robust uncertainty estimates for various regression tasks.
In surgical computer vision applications, obtaining labeled training data is challenging due to data-privacy concerns and the need for expert annotation. Unpaired image-to-image translation techniques have been explored to automatically generate large annotated datasets by translating synthetic images to the realistic domain. However, preserving the structure and semantic consistency between the input and translated images presents significant challenges, mainly when there is a distributional mismatch in the semantic characteristics of the domains. This study empirically investigates unpaired image translation methods for generating suitable data in surgical applications, explicitly focusing on semantic consistency. We extensively evaluate various state-of-the-art image translation models on two challenging surgical datasets and downstream semantic segmentation tasks. We find that a simple combination of structural-similarity loss and contrastive learning yields the most promising results. Quantitatively, we show that the data generated with this approach yields higher semantic consistency and can be used more effectively as training data.
We consider the problem of learning observation models for robot state estimation with incremental non-differentiable optimizers in the loop. Convergence to the correct belief over the robot state is heavily dependent on a proper tuning of observation models which serve as input to the optimizer. We propose a gradient-based learning method which converges much quicker to model estimates that lead to solutions of much better quality compared to an existing state-of-the-art method as measured by the tracking accuracy over unseen robot test trajectories.
We investigate the complexity of several manipulation and control problems under numerous prevalent approval-based multiwinner voting rules. Particularly, the rules we study include approval voting (AV), satisfaction approval voting (SAV), net-satisfaction approval voting (NSAV), proportional approval voting (PAV), approval-based Chamberlin-Courant voting (ABCCV), minimax approval voting (MAV), etc. We show that these rules generally resist the strategic types scrutinized in the paper, with only a few exceptions. In addition, we also obtain many fixed-parameter tractability results for these problems with respect to several natural parameters, and derive polynomial-time algorithms for certain special cases.
The edge processing of deep neural networks (DNNs) is becoming increasingly important due to its ability to extract valuable information directly at the data source to minimize latency and energy consumption. Frequency-domain model compression, such as with the Walsh-Hadamard transform (WHT), has been identified as an efficient alternative. However, the benefits of frequency-domain processing are often offset by the increased multiply-accumulate (MAC) operations required. This paper proposes a novel approach to an energy-efficient acceleration of frequency-domain neural networks by utilizing analog-domain frequency-based tensor transformations. Our approach offers unique opportunities to enhance computational efficiency, resulting in several high-level advantages, including array micro-architecture with parallelism, ADC/DAC-free analog computations, and increased output sparsity. Our approach achieves more compact cells by eliminating the need for trainable parameters in the transformation matrix. Moreover, our novel array micro-architecture enables adaptive stitching of cells column-wise and row-wise, thereby facilitating perfect parallelism in computations. Additionally, our scheme enables ADC/DAC-free computations by training against highly quantized matrix-vector products, leveraging the parameter-free nature of matrix multiplications. Another crucial aspect of our design is its ability to handle signed-bit processing for frequency-based transformations. This leads to increased output sparsity and reduced digitization workload. On a 16$\times$16 crossbars, for 8-bit input processing, the proposed approach achieves the energy efficiency of 1602 tera operations per second per Watt (TOPS/W) without early termination strategy and 5311 TOPS/W with early termination strategy at VDD = 0.8 V.
Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory demands. In addition, the efficiency of a deep ensemble is related to diversity among the ensemble members which is challenging for large, over-parameterized deep neural networks. Moreover, ensemble learning has not yet seen such widespread adoption, and it remains a challenging endeavor for self-supervised or unsupervised representation learning. Motivated by these challenges, we present a novel self-supervised training regime that leverages an ensemble of independent sub-networks, complemented by a new loss function designed to encourage diversity. Our method efficiently builds a sub-model ensemble with high diversity, leading to well-calibrated estimates of model uncertainty, all achieved with minimal computational overhead compared to traditional deep self-supervised ensembles. To evaluate the effectiveness of our approach, we conducted extensive experiments across various tasks, including in-distribution generalization, out-of-distribution detection, dataset corruption, and semi-supervised settings. The results demonstrate that our method significantly improves prediction reliability. Our approach not only achieves excellent accuracy but also enhances calibration, surpassing baseline performance across a wide range of self-supervised architectures in computer vision, natural language processing, and genomics data.
Transparency and accountability are indispensable principles for modern data protection, from both, legal and technical viewpoints. Regulations such as the GDPR, therefore, require specific transparency information to be provided including, e.g., purpose specifications, storage periods, or legal bases for personal data processing. However, it has repeatedly been shown that all too often, this information is practically hidden in legalese privacy policies, hindering data subjects from exercising their rights. This paper presents a novel approach to enable large-scale transparency information analysis across service providers, leveraging machine-readable formats and graph data science methods. More specifically, we propose a general approach for building a transparency analysis platform (TAP) that is used to identify data transfers empirically, provide evidence-based analyses of sharing clusters of more than 70 real-world data controllers, or even to simulate network dynamics using synthetic transparency information for large-scale data-sharing scenarios. We provide the general approach for advanced transparency information analysis, an open source architecture and implementation in the form of a queryable analysis platform, and versatile analysis examples. These contributions pave the way for more transparent data processing for data subjects, and evidence-based enforcement processes for data protection authorities. Future work can build upon our contributions to gain more insights into so-far hidden data-sharing practices.
Non-hydrostatic atmospheric models often use semi-implicit temporal discretisations in order to negate the time step limitation of explicitly resolving the fast acoustic and gravity waves. Solving the resulting system to machine precision using Newton's method is considered prohibitively expensive, and so the non-linear solver is typically truncated to a fixed number of iterations, using an approximate Jacobian matrix that is reassembled only once per time step. The present article studies the impact of using various third-order, four stage Rosenbrock-Wanner schemes, where integration weights are chosen to meet specific stability and order conditions, in comparison to a Crank-Nicolson time discretisation, as is done in the UK Met Office's LFRic model. Rosenbrock-Wanner schemes present a promising alternative on account of their ability to preserve their temporal order with only an approximate Jacobian, and may be constructed to be stiffly-stable, so as to ensure the decay of fast unresolved modes. These schemes are compared for the 2D rotating shallow water equations and the 3D compressible Euler equations at both planetary and non-hydrostatic scales and are shown to exhibit improved results in terms of their energetic profiles and stability. Results in terms of computational performance are mixed, with the Crank-Nicolson method allowing for longer time steps and faster time to solution for the baroclinic instability test case at planetary scales, and the Rosenbrock-Wanner methods allowing for longer time steps and faster time to solution for a rising bubble test case at non-hydrostatic scales.
Graph neural networks (GNNs) have been demonstrated to be a powerful algorithmic model in broad application fields for their effectiveness in learning over graphs. To scale GNN training up for large-scale and ever-growing graphs, the most promising solution is distributed training which distributes the workload of training across multiple computing nodes. However, the workflows, computational patterns, communication patterns, and optimization techniques of distributed GNN training remain preliminarily understood. In this paper, we provide a comprehensive survey of distributed GNN training by investigating various optimization techniques used in distributed GNN training. First, distributed GNN training is classified into several categories according to their workflows. In addition, their computational patterns and communication patterns, as well as the optimization techniques proposed by recent work are introduced. Second, the software frameworks and hardware platforms of distributed GNN training are also introduced for a deeper understanding. Third, distributed GNN training is compared with distributed training of deep neural networks, emphasizing the uniqueness of distributed GNN training. Finally, interesting issues and opportunities in this field are discussed.
Deep neural networks have revolutionized many machine learning tasks in power systems, ranging from pattern recognition to signal processing. The data in these tasks is typically represented in Euclidean domains. Nevertheless, there is an increasing number of applications in power systems, where data are collected from non-Euclidean domains and represented as the graph-structured data with high dimensional features and interdependency among nodes. The complexity of graph-structured data has brought significant challenges to the existing deep neural networks defined in Euclidean domains. Recently, many studies on extending deep neural networks for graph-structured data in power systems have emerged. In this paper, a comprehensive overview of graph neural networks (GNNs) in power systems is proposed. Specifically, several classical paradigms of GNNs structures (e.g., graph convolutional networks, graph recurrent neural networks, graph attention networks, graph generative networks, spatial-temporal graph convolutional networks, and hybrid forms of GNNs) are summarized, and key applications in power systems such as fault diagnosis, power prediction, power flow calculation, and data generation are reviewed in detail. Furthermore, main issues and some research trends about the applications of GNNs in power systems are discussed.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191