Batch version of the back-propagation algorithm. ％ Given a set of corresponding input-output pairs and an initial network ％ [W1,W2,critvec,iter]=batbp(NetDef,W1,W2,PHI,Y,trparms) trains the ％ network with backpropagation. ％ ％ The activation functions must be either linear or tanh. The network ％ architecture is defined by the matrix NetDef consisting of two ％ rows. The first row specifies the hidden layer while the second ％ specifies the output layer. ％
標簽： back-propagation corresponding input-output algorithm
上傳時間： 2016-12-27
上傳用戶：exxxds
％ Train a two layer neural network with the Levenberg-Marquardt ％ method. ％ ％ If desired, it is possible to use regularization by ％ weight decay. Also pruned (ie. not fully connected) networks can ％ be trained. ％ ％ Given a set of corresponding input-output pairs and an initial ％ network, ％ [W1,W2,critvec,iteration,lambda]=marq(NetDef,W1,W2,PHI,Y,trparms) ％ trains the network with the Levenberg-Marquardt method. ％ ％ The activation functions can be either linear or tanh. The ％ network architecture is defined by the matrix NetDef which ％ has two rows. The first row specifies the hidden layer and the ％ second row specifies the output layer.
標簽： Levenberg-Marquardt desired network neural
上傳時間： 2016-12-27
上傳用戶：jcljkh
Train a two layer neural network with a recursive prediction error ％ algorithm ("recursive Gauss-Newton"). Also pruned (i.e., not fully ％ connected) networks can be trained. ％ ％ The activation functions can either be linear or tanh. The network ％ architecture is defined by the matrix NetDef , which has of two ％ rows. The first row specifies the hidden layer while the second ％ specifies the output layer.
標簽： recursive prediction algorithm Gauss-Ne
上傳時間： 2016-12-27
上傳用戶：ljt101007
The code performs a number (ITERS) of iterations of the Bailey s 6-step FFT algorithm (following the ideas in the CMU Task parallel suite). 1.- Generates an input signal vector (dgen) with size n=n1xn2 stored in row major order In this code the size of the input signal is NN=NxN (n=NN, n1=n2=N) 2.- Transpose (tpose) A to have it stored in column major order 3.- Perform independent FFTs on the rows (cffts) 4.- Scale each element of the resulting array by a factor of w[n]**(p*q) 5.- Transpose (tpose) to prepair it for the next step 6.- Perform independent FFTs on the rows (cffts) 7.- Transpose the resulting matrix The code requires nested Parallelism.
標簽： iterations performs Bailey number
上傳時間： 2014-01-05
上傳用戶：libenshu01
#include <stdio.h> #include <stdlib.h> #define SMAX 100 typedef struct SPNode { int i,j,v; }SPNode; struct sparmatrix { int rows,cols,terms; SPNode data [SMAX]; }; sparmatrix CreateSparmatrix() { sparmatrix A; printf("\n\t\t請輸入稀疏矩陣的行數，列數和非零元素個數（用逗號隔開）:"); scanf("%d,%d,%d",&A.cols,&A.terms); for(int n=0;n<=A.terms-1;n++) { printf("\n\t\t輸入非零元素值（格式：行號，列號，值）:"); scanf("%d,%d,%d",&A.data[n].i,&A.data[n].j,&A.data[n].v); } return A; } void ShowSparmatrix(sparmatrix A) { int k; printf("\n\t\t"); for(int x=0;x<=A.rows-1;x++) { for(int y=0;y<=A.cols-1;y++) { k=0; for(int n=0;n<=A.terms-1;n++) { if((A.data[n].i-1==x)&&(A.data[n].j-1==y)) { printf("%8d",A.data[n].v); k=1; } } if(k==0) printf("%8d",k); } printf("\n\t\t"); } } void sumsparmatrix(sparmatrix A) { SPNode *p; p=(SPNode*)malloc(sizeof(SPNode)); p->v=0; int k; k=0; printf("\n\t\t"); for(int x=0;x<=A.rows-1;x++) { for(int y=0;y<=A.cols-1;y++) { for(int n=0;n<=A.terms;n++) { if((A.data[n].i==x)&&(A.data[n].j==y)&&(x==y)) { p->v=p->v+A.data[n].v; k=1; } } } printf("\n\t\t"); } if(k==1) printf("\n\t\t對角線元素的和：:%d\n",p->v); else printf("\n\t\t對角線元素的和為：:0"); } int main() { int ch=1,choice; struct sparmatrix A; A.terms=0; while(ch) { printf("\n"); printf("\n\t\t 稀疏矩陣的三元組系統 "); printf("\n\t\t*********************************"); printf("\n\t\t 1------------創建 "); printf("\n\t\t 2------------顯示 "); printf("\n\t\t 3------------求對角線元素和"); printf("\n\t\t 4------------返回 "); printf("\n\t\t*********************************"); printf("\n\t\t請選擇菜單號（0-3）:"); scanf("%d",&choice); switch(choice) { case 1: A=CreateSparmatrix(); break; case 2: ShowSparmatrix(A); break; case 3: SumSparmatrix(A); break; default: system("cls"); printf("\n\t\t輸入錯誤！請重新輸入！\n"); break; } if (choice==1||choice==2||choice==3) { printf("\n\t\t"); system("pause"); system("cls"); } else system("cls"); } }
上傳時間： 2020-06-11
上傳用戶：ccccy
