This work theoretically investigates the performance of a composite neural network. A composite neural network is a rooted directed acyclic graph combining a set of pre-trained and non-instantiated neural network models, where a pre-trained neural network model is well-crafted for a specific task and targeted to approximate a specific function with instantiated weights. The advantages of adopting such a pre-trained model in a composite neural network are two folds. One is to benefit from other's intelligence and diligence, and the other is saving the efforts in data preparation and resources and time in training. However, the overall performance of composite neural network is still not clear. In this work, we prove that a composite neural network, with high probability, performs better than any of its pre-trained components under certain assumptions. In addition, if an extra pre-trained component is added to a composite network, with high probability the overall performance will be improved. In the empirical evaluations, distinctively different applications support the above findings.
An Advanced Physics-Informed Neural Operator for Comprehensive Design Optimization of Highly-Nonlinear Systems: An Aerospace Composites Processing Case Study
The Good, the Bad and the Ugly: Evaluating Convolutional Neural Networks for Prohibited Item Detection Using Real and Synthetically Composited X-ray Imagery
Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
The University of Texas at Dallas(德克萨斯大学达拉斯分校);US Army Research Laboratory(美国陆军研究实验室);University of Oslo(奥斯陆大学);Virginia Tech(弗吉尼亚理工大学);University of the District of Columbia(哥伦比亚特区大学)
Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks
Graduate Group in Applied Mathematics and Computational Science(应用数学与计算科学联合研究生组);University of Pennsylvania(宾夕法尼亚大学);Department of Mechanical Engineering and Applied Mechanics(机械工程与应用力学系)
A physical adaptive material motor unit neural network: a hygromorph composite material machine
Bristol Composites Institute, School of Civil, Aerospace and Mechanical Engineering, University of Bristol(布里斯托尔复合材料研究所,土木、航空航天与机械工程学院,布里斯托尔大学);School of Architecture, University of Waterloo(滑铁卢大学建筑学院);Research School of Chemistry and John Curtin School of Medical Research, Australian National University(化学研究学校和约翰·库廷医学研究学院,澳大利亚国立大学);School of Cellular and Molecular Medicine, University of Bristol(细胞与分子医学学院,布里斯托尔大学);School of Engineering Mathematics and Technology, University of Bristol(工程数学与技术学院,布里斯托尔大学);Bristol Robotics Lab, Bristol, United Kingdom(布里斯托尔机器人实验室,布里斯托尔,英国)
Integrating Wide and Deep Neural Networks with Squeeze-and-Excitation Blocks for Multi-Target Property Prediction in Additively Manufactured Fiber Reinforced Composites
Department of Mechanical Engineering, Southern Methodist University(机械工程系,南方 Methodist 大学)
Physics-Informed Neural Network Modeling of Biodegradable Contaminant Transport through GCL/SL Composite Liners
Department of Civil, Environmental, and Infrastructure Engineering, George Mason University(乔治·马歇尔大学土木、环境与基础设施工程系);State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences(中国科学院寒区工程与冻土科学联合实验室,西北生态环境资源研究院);Laboratoire Navier/CERMES, École Nationale des Ponts et Chaussées, Institut Polytechnique de Paris(巴黎理工学院劳达实验室/塞姆斯实验室,法国国家桥梁与道路学院)
Explainable Prediction of the Mechanical Properties of Composites with CNNs
Department of Mechanical Engineering, Imperial College London, UK(帝国理工学院机械工程系);Department of Computing, Imperial College London, UK(帝国理工学院计算系);Department of Informatics, King's College London, UK(伦敦国王学院信息学系)