46 MLPTrain * mlp_init(int *topo, int nbLayers, float *inputs, float *outputs, int nbSamples)  in mlp_init()  argument
70         for (i=0;i<nbSamples;i++)  in mlp_init()
75         inMean[j] /= nbSamples;  in mlp_init()
76         std /= nbSamples;  in mlp_init()
97         for (i=0;i<nbSamples;i++)  in mlp_init()
99         mean /= nbSamples;  in mlp_init()
111 double compute_gradient(MLPTrain *net, float *inputs, float *outputs, int nbSamples, double *W0_gra…  in compute_gradient()  argument
138     for (s=0;s<nbSamples;s++)  in compute_gradient()
195     int nbSamples;  member
218 …arg->rms = compute_gradient(arg->net, arg->inputs, arg->outputs, arg->nbSamples, arg->W0_grad, arg…  in gradient_thread_process()
225 float mlp_train_backprop(MLPTrain *net, float *inputs, float *outputs, int nbSamples, int nbEpoch, …  in mlp_train_backprop()  argument
245     int samplePerPart = nbSamples/NB_THREADS;  in mlp_train_backprop()
278     rate /= nbSamples;  in mlp_train_backprop()
290         args[i].nbSamples = samplePerPart;  in mlp_train_backprop()
320         rms = (rms/(outDim*nbSamples));  in mlp_train_backprop()
321         error_rate[0] = (error_rate[0]/(nbSamples));  in mlp_train_backprop()
322         error_rate[1] = (error_rate[1]/(nbSamples));  in mlp_train_backprop()
429     int nbSamples;  in main()  local
445     nbSamples = atoi(argv[4]);  in main()
448     inputs = malloc(nbInputs*nbSamples*sizeof(*inputs));  in main()
449     outputs = malloc(nbOutputs*nbSamples*sizeof(*outputs));  in main()
459     for (i=0;i<nbSamples;i++)  in main()
467             nbSamples = i;  in main()
474     fprintf (stderr, "Got %d samples\n", nbSamples);  in main()
475     net = mlp_init(topo, 3, inputs, outputs, nbSamples);  in main()
476     rms = mlp_train_backprop(net, inputs, outputs, nbSamples, nbEpoch, 1);  in main()