Generative Adversarial Networks (GANs) are widely used for modeling complex data. However, the dynamics of the gradient descent-ascent (GDA) algorithms, often used for training GANs, have been notoriously difficult to...
详细信息
Generative Adversarial Networks (GANs) are widely used for modeling complex data. However, the dynamics of the gradient descent-ascent (GDA) algorithms, often used for training GANs, have been notoriously difficult to analyze. We study these dynamics in the case where the discriminator is kernel-based and the true distribution consists of discrete points in Euclidean space. Prior works have analyzed the GAN dynamics in such scenarios via simple linearization close to the equilibrium. In this work, we show that linearized analysis can be grossly inaccurate, even at moderate distances from the equilibrium. We then propose an alternative non-linear yet tractable second moment model. The proposed model predicts the convergence behavior well and reveals new insights about the role of the kernel width on convergence rate, not apparent in the linearized analysis. These insights suggest certain shapes of the kernel offer both fast local convergence and improved global convergence. We corroborate our theoretical results through simulations.
Spray drying is a common a technique in process engineering, involving analysis tasks for large-scale multiphysics mechanisms, typically addressed using Computational Fluid Dynamics (CFD) software based on Finite Elem...
详细信息
作者：
Huang, WenjunCui, YunduanLi, HuiyunWu, XinyuUniv Chinese Acad Sci
Sch Artificial Intelligence Beijing 101408 Peoples R China Chinese Acad Sci
Shenzhen Inst Adv Technol Shenzhen 518055 Guangdong Peoples R China Chinese Acad Sci
Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sys Shenzhen 518055 Guangdong Peoples R China Chinese Acad Sci
Shenzhen Inst Adv Technol Guangdong Hong Kong Macao Joint Lab Human Machine Shenzhen 518055 Guangdong Peoples R China
Gaussian process (GP) offers a robust solution for modeling the dynamics of unmanned surface vehicles (USV) in model-based reinforcement learning (MBRL). However, the rapidly increasing computational complexity with a...
详细信息
Gaussian process (GP) offers a robust solution for modeling the dynamics of unmanned surface vehicles (USV) in model-based reinforcement learning (MBRL). However, the rapidly increasing computational complexity with a large sample capacity of GP limits its application in complex scenarios that require substantial samples to cover the state space. In this article, a novel probabilistic MBRL approach, probabilistic neural networks model predictive control (PNMPC) is proposed to tackle this issue. With an iterative learning framework, PNMPC properly models the USV dynamics using neural networks from a probabilistic perspective to avoid the computational complexity associated with sample capacity. Employing this model to effectively propagate system uncertainties, a model predictive control (MPC) policy is developed to robustly control the USV against external disturbances. Evaluated by position-keeping and multiple targets-tracking scenarios on a real USV data-driven simulation, the proposed method consistently demonstrates its significant superiority in both model accuracy and control performance compared to not only GP model-based approaches but also the probabilistic neural networks-based MBRL baselines, across various scales of external disturbances.
This paper presents a novel learning analytics method: Transition Network analysis (TNA), a method that integrates Stochastic process Mining and probabilistic graph representation to model, visualize, and identify tra...
详细信息
ISBN:
(纸本)9798400707018
This paper presents a novel learning analytics method: Transition Network analysis (TNA), a method that integrates Stochastic process Mining and probabilistic graph representation to model, visualize, and identify transition patterns in the learning processdata. Combining the relational and temporal aspects into a single lens offers capabilities beyond either framework, including centralities to capture important learning events, community detection to identify behavior patterns, and clustering to reveal temporal patterns. Furthermore, TNA introduces several significance tests that go beyond either method and add rigor to the analysis. Here, we introduce the theoretical and mathematical foundations of TNA and we demonstrate the functionalities of TNA with a case study where students (n=191) engaged in small-group collaboration to map patterns of group dynamics using the theories of co-regulation and socially-shared regulated learning. The analysis revealed that TNA can map the regulatory processes as well as identify important events, patterns, and clusters. Bootstrap validation established the significant transitions and eliminated spurious transitions. As such, TNA can capture learning dynamics and provide a robust framework for investigating the temporal evolution of learning processes. Future directions include -inter alia- expanding estimation methods, reliability assessment, and building longitudinal TNA.
Achieving optimization and control of industrial processes relies on accurate models. This paper proposes a combined data model for modeling complex industrial processes, utilizing a graph convolutional network and an...
详细信息
The additive-manufacturing (AM) field necessitates a robust process-monitoring system for quality assurance and control. To meet this industrial requirement, quality-evaluation models have emerged as powerful tools fo...
详细信息
The additive-manufacturing (AM) field necessitates a robust process-monitoring system for quality assurance and control. To meet this industrial requirement, quality-evaluation models have emerged as powerful tools for providing quality feedback. Recently, convolutional-neural-network- (CNN)-based classification models have gained popularity in quality evaluation using image data. However, such models require sufficient image data for training, a requirement that is challenging to fulfill in the context of metallic AM due to the complexity of decomposition and analysis. This challenge is particularly pronounced in start-up or medium-sized metallic-AM enterprises. Moreover, many countries around the world have faced a decline in population and a shortage of labor in the engineering field. This growing shortage of workers to collect datasets exacerbates this challenge. In this study, experiments of directed-energy-deposition (DED) processes for single-line and single-track metallic deposition using AISI 316 L stainless-steel powders were conducted with two experimenters. After the process, a minimal amount of cross-sectional surface image data of the metallic deposition was binary-processed and analyzed across three quality states: normal state, surface burrs, and internal defects. To compensate for the lack of training data, multiple strategies are proposed, including image preprocessing and ResNet transfer learning. The selection of an optimization solver and layer depth for maximizing classification performance was discussed. The potential performance of ResNet dealing with binary images and performance standards with few training data was also identified by comparing with other higher-level architectures (Inception and Xcepition).
1,3-propanediol (1,3-PDO) is a significant product of fermentation, with glycerol serving as the primary substrate in most cases. Bioprocesscontrol based on real-time information of feedstock and main products is cru...
详细信息
1,3-propanediol (1,3-PDO) is a significant product of fermentation, with glycerol serving as the primary substrate in most cases. Bioprocesscontrol based on real-time information of feedstock and main products is crucial for reducing the cost of production. However, rapid quantification of 1,3-PDO and glycerol remains challenging due to their highly similar molecular structures. In this study, the feasibility of near-infrared (NIR) spectroscopy to monitor 1,3-PDO, glycerol, acetate, and butyrate concentrations in the fermentation process using strain Clostridium pasteurianum was evaluated. NIR spectra were acquired through at-line measurement involving sampling and ex-situ analysis or on-line measurement with a fiber optic probe immersed in fermentation broth, integrated with Partial Least Squares (PLS) regression to establish calibration models on a laboratory-scale and pilot-scale. The best PLS regressions of 1,3-PDO, glycerol, acetate, and butyrate with two measurement approaches provided excellent performance, with the root-mean-squared errors of prediction (RMSEP) of 1.656 g/L, 1.502 g/L, 0.746 g/L, and 0.557 g/L in at-line measurement and 1.113 g/L, 1.581 g/L, 0.415 g/L, and 0.526 g/L in on-line measurement. The cross-scale application performance of at-line measurement was evaluated by an external fermentation trial and an acceptable result was achieved. At-line measurement technique represents a superior choice for the optimization of fermentation process since the robustness across varying fermentation scales and its applicability in multiple bioreactors. Thus, a calibration model developed for one bioreactor is likely to be used in other bioreactors, which enables the reduction of modeling costs. On-line measurement technique, owing to its automated operation and frequent data acquisition, enables real-time monitoring and precise control of the fermentation process, thereby reducing cost and improving production efficiency.
Path tracking control is a fundamental technology in autonomous vehicle applications, but it faces significant challenges related to vehicle modeling and external disturbances. In this paper, an improved model-free ad...
详细信息
Hospitals currently face numerous challenges in managing their pharmacy operations efficiently. While Business process Reengineering (BPR) has been proposed as a solution, its implementation in healthcare is more comp...
详细信息
Cavity pressure control can enhance the repeatability of injection molding processes. While extensive research has focused on thermoplastic cavity pressure control, there is a notable gap in models and control strateg...
详细信息
暂无评论