资源描述
单击此处编辑母版标题样式,单击此处编辑母版文本样式,第二级,第三级,第四级,第五级,2017/12/19,#,English Presentation,Title,A review on neural networks with random weights.,Contents,1,Shallow feed-forword neural network with random weights(NNRWs).,2,Deep neural network with random weights.,3,Conclusion.,1 Shallow,feed-forword neural network with random weights,1.1 Turing,The father of AI,(artificial intelligence),Turing Test,Can Machines,Think?,1.3 RVFL(random,v,ector,f,unctional,l,ink,n,etworks),-1,1,MooreCPenrose,pseudo-inverse.,1.4 ELM(extreme learning,machine),Zero,One unified,form,generalized,2 Deep NNRWs(neural networkwith random weights),2.1 AE(auto-encoder)+NNRWs,3-layer,Unsupervised,learning,2.2 RBM(restricted,b,oltzmann machines)+NNRWs,Two layers,Fully connected,No connections,i,n the same layer,3 conclusion,Advantages:,Faster learning speed,Improve the computing efficiency.,Disadvantages:,The randomization range.,The type of distribution of the hidden weights.,Cao,W,Wang X,Ming Z,et al.A Review on Neural Networks with Random WeightsJ.Neurocomputing,2017.,Thank you,
展开阅读全文