To improve the performance of multilayer perceptron(MLP)neural networks activated by conventional activation functions,this paper presents a new MLP activated by univariate Gaussian radial basis functions(RBFs)with ad...To improve the performance of multilayer perceptron(MLP)neural networks activated by conventional activation functions,this paper presents a new MLP activated by univariate Gaussian radial basis functions(RBFs)with adaptive centers and widths,which is composed of more than one hidden layer.In the hidden layer of the RBF-activated MLP network(MLPRBF),the outputs of the preceding layer are first linearly transformed and then fed into the univariate Gaussian RBF,which exploits the highly nonlinear property of RBF.Adaptive RBFs might address the issues of saturated outputs,low sensitivity,and vanishing gradients in MLPs activated by other prevailing nonlinear functions.Finally,we apply four MLP networks with the rectified linear unit(ReLU),sigmoid function(sigmoid),hyperbolic tangent function(tanh),and Gaussian RBF as the activation functions to approximate the one-dimensional(1D)sinusoidal function,the analytical solution of viscous Burgers’equation,and the two-dimensional(2D)steady lid-driven cavity flows.Using the same network structure,MLP-RBF generally predicts more accurately and converges faster than the other threeMLPs.MLP-RBF using less hidden layers and/or neurons per layer can yield comparable or even higher approximation accuracy than other MLPs equipped with more layers or neurons.展开更多
There is no doubt that COVID-19 outbreak is currently the biggest public health threat,which has caused catastrophic con sequences in many countries and regions.As host immunity is key to fighting against virus infect...There is no doubt that COVID-19 outbreak is currently the biggest public health threat,which has caused catastrophic con sequences in many countries and regions.As host immunity is key to fighting against virus infection,it is important to characterize the immunologic changes in the COVID-19 patients,and to explore potential therapeutic candidates.The most efficient ways to end this pandemic are to vaccinate the susceptible population,and to use specific drugs,such as monoclonal antibodies against the viral spike protein(S protein),to treat the affected individuals.Several promising neutralizing antibodies have recently been reported(Cao et al.,2020;Lv et al.,2020).展开更多
基金This work was partially supported by the research grant of the National University of Singapore(NUS),Ministry of Education(MOE Tier 1).
文摘To improve the performance of multilayer perceptron(MLP)neural networks activated by conventional activation functions,this paper presents a new MLP activated by univariate Gaussian radial basis functions(RBFs)with adaptive centers and widths,which is composed of more than one hidden layer.In the hidden layer of the RBF-activated MLP network(MLPRBF),the outputs of the preceding layer are first linearly transformed and then fed into the univariate Gaussian RBF,which exploits the highly nonlinear property of RBF.Adaptive RBFs might address the issues of saturated outputs,low sensitivity,and vanishing gradients in MLPs activated by other prevailing nonlinear functions.Finally,we apply four MLP networks with the rectified linear unit(ReLU),sigmoid function(sigmoid),hyperbolic tangent function(tanh),and Gaussian RBF as the activation functions to approximate the one-dimensional(1D)sinusoidal function,the analytical solution of viscous Burgers’equation,and the two-dimensional(2D)steady lid-driven cavity flows.Using the same network structure,MLP-RBF generally predicts more accurately and converges faster than the other threeMLPs.MLP-RBF using less hidden layers and/or neurons per layer can yield comparable or even higher approximation accuracy than other MLPs equipped with more layers or neurons.
基金This work was partially supported by the National Natural Science Foundation of China (Grant Nos. 11371187, 11501257) and Jiangsu University of Technology of China (KYY14015, KYY14016).
基金This work was funded by the National Natural Science Foundation of China(Nos.61822108,62041102 and 62032007 to Q.J.)the Emergency Research Project for COVID-19 of Harbin Institute of Technology(No.2020-001 to Q.J.)the Scientific Research Project Approved by Heilongjiang Provincial Health Committee(No.2019-253 to J.L.).
文摘There is no doubt that COVID-19 outbreak is currently the biggest public health threat,which has caused catastrophic con sequences in many countries and regions.As host immunity is key to fighting against virus infection,it is important to characterize the immunologic changes in the COVID-19 patients,and to explore potential therapeutic candidates.The most efficient ways to end this pandemic are to vaccinate the susceptible population,and to use specific drugs,such as monoclonal antibodies against the viral spike protein(S protein),to treat the affected individuals.Several promising neutralizing antibodies have recently been reported(Cao et al.,2020;Lv et al.,2020).