Accelerating automatic model finding with layer replications case study of MobileNetV2. by Kritpawit Soongswang, Chantana Chantrapornchai

“…Our experiments demonstrate the effectiveness of the automatic model finding process for layer replication, using both distributed data-parallel and concurrent training under different conditions. …”
Get full text

Comparison of Kolmogorov–Arnold Networks and Multi-Layer Perceptron for modelling and optimisation analysis of energy systems by Talha Ansar, Waqar Muhammad Ashraf

Get full text

Additional stress transfer model of double layer dielectric foundation on thin topsoil covered area by Chao GAO, Guocan TIAN, Naizhong XU, Yujun ZHANG

“…In view of the few and imperfect models for calculating the additional stress and the depth of load effect on thin topsoil layer area, it is necessary to further investigate the additional stress transfer model of double layer elastic medium foundation from the perspective of simple calculation process, fewer parameters and easy access. …”
Get full text

Distribution Network Security Situation Awareness Method Based on the Distribution Network Topology Layered Model by Yuhong Ouyang, Man Li, Wenqian Kang, Xiangbei Che, Ruixian Ye

“…In response to the rapid and accurate distribution network security situation awareness requirements, this paper proposes a distribution network security situation awareness method based the distribution network topology layered model. First, a hierarchical model of the distribution network topology under the premise of optimizing the location of the synchronous phasor measuring device is constructed. …”
Get full text

A two‐stage, four‐layer robust optimisation model for distributed cooperation in multi‐microgrids by Haobo Rong, Jianhui Wang, Honghai Kuang

“…The proposed model follows a two‐stage, four‐layer ‘min‐min‐max‐min’ structure. …”
Get full text

Influence of Fissure Number on the Mechanical Properties of Layer-Crack Rock Models under Uniaxial Compression by Yun-liang Tan, Wei-yao Guo, Tong-bin Zhao, Feng-hai Yu, Bin Huang, Dong-mei Huang

“…Understanding the mechanical properties of layer-crack rock models is beneficial for rational design and stability analysis of rock engineering project and rock burst prevention. …”
Get full text

Computationally Effective Gravity Inversion Allows for High-Resolution Regional Density Modeling of Earth's Crust with the Inclusion of the Topography Layer by Martyshko Pyotr, Byzov Denis, Chernoskutov Aleksandr

“…In this paper however, we will address those issues simultaneously, offering a complete and computationally effective method of recovering spherical density model of Earth's crust with the upper topography layer. …”
Get full text

DNN-MPC Control Based on Two-Layer Optimization Method for the COGAG System by Jingjing Zhang, Jian Li, Xuemin Li, Xiuzhen Ma

“…An engine-propeller cooperative control based on model predictive control (MPC), which takes a deep neural network (DNN) as the prediction model, is studied, and a two-layer optimization method is proposed to improve the economy and maneuverability of the COGAG system. …”
Get full text

Exploring the Effects of Support Restoration on Pictorial Layers Through Multi-Resolution 3D Survey by Emma Vannini, Silvia Belardi, Irene Lunghi, Alice Dal Fovo, Raffaella Fontana

“…By processing and cross-comparing 3D point cloud data from both techniques, we quantified shape variations and evaluated their impact on the pictorial layers. …”
Get full text

How Variable Are Cold Pools? by Leah D. Grant, Bastian Kirsch, Jennie Bukowski, Nicholas M. Falk, Christine A. Neumaier, Mirjana Sakradzija, Susan C. van denHeever, Felix Ament

Subjects: Get full text

Antenna Optimization Design Based on Deep Gaussian Process Model by Xin-Yu Zhang, Yu-Bo Tian, Xie Zheng

“…When using Gaussian process (GP) machine learning as a surrogate model combined with the global optimization method for rapid optimization design of electromagnetic problems, a large number of covariance calculations are required, resulting in a calculation volume which is cube of the number of samples and low efficiency. …”
Get full text

Comparison of classical, xgboost and neural network methods for parameter estimation in epidemic processes on random graphs by Ágnes Backhausz, Edit Bognár, Villő Csiszár, Damján Tárkányi, András Zempléni

Get full text

A Matching Game for LLM Layer Deployment in Heterogeneous Edge Networks by Benedetta Picano, Dinh Thai Hoang, Diep N. Nguyen

“…This mutual selection process minimizes inference latency in the learning process and models the bubble time as game externalities, assuming a sequential pipeline execution. …”
Get full text

Applying the language acquisition model to the solution small language processing tasks by Dz. I. Kachkou

“…Based on the current understanding of the language acquisition and existing computer models of this process, the architecture of the system of small language processing, which is taught through modeling of ontogenesis, is proposed. …”
Get full text

Network Management System's Data Management Layer Based on Big Data Technology by Wei Li

“…Data management layer is the core of data processing and management in network management system.The current situation and problems of network management system was introduced.To break the isolation between the professional network management system and promote data sharing,data domain should further be subdivided and the data model should be reconstructed,and technical framework of Hadoop+MPP was a better choice.The direction for the planning and design of the network management system was pointed out.Finally,the relation of data management layer platform and enterprise wide data sharing service platform was discussed.…”
Get full text

A neural master equation framework for multiscale modeling of molecular processes: application to atomic-scale plasma processes by Shoubhanik Nath, Joseph R. Vella, David B. Graves, Ali Mesbah

“…The framework is demonstrated for multiscale modeling of Si atomic layer etching and reactive ion etching, where the learned NME-based surface kinetic models exhibit good predictive and extrapolative capabilities for predicting experimentally relevant observables as a function of process parameters. …”
Get full text

Modeling of quality characteristics of the surface layer hardened by free-moving indenters under rotating electromagnetic field by Valery A. Lebedev, Anatoly A. Kochubey, Irina V. Chumak

“…A comparative analysis of the experimental data obtained in the process of the magneto-dynamic processing with the calculated ones shows the applicability of the proposed models for predicting quality parameters of the hardened surface layer.…”
Get full text

Parametric evaluation and predictive modelling of formability in μ-SPIF process by Sahu Vijay Kumar, Das Purnendu, Adhikary Avishek, Bandyopadhyay Kaushik

“…Machine learning regression models e.g. Tri-layered Neural Network, Quadratic Support Vector Machine, and Gaussian Process Regression are developed based on experimental data to predict the formed height and the surface roughness. …”
Get full text

Establishment of a Prediction Model for the Residual Stress on the Surface Layer of Face Gears During Hot Rolling by Jin Yuanyuan, Xu Hongyu, Li Li, Zhang Fengshou, Wang Xiaoqiang, Zhang Guang

“…Taking the simulation results as data samples, the response surface method is used to establish the prediction model of residual compressive stress and compressive stress layer depth on the surface of hot rolling gear profiles, and the optimal process combination is obtained by taking the maximum peak value of residual compressive stress and the minimum depth of residual compressive stress layer as the optimization objective. …”
Get full text

High-Performance and Lightweight AI Model with Integrated Self-Attention Layers for Soybean Pod Number Estimation by Qian Huang

Get full text