代码搜索结果

銷EURAL NET TRAINED BY GENETIC ALGORITHM Looking this Project is the easiest way to understand how to Train a Neural Net with a Genetic Algorithm. In This Case 3 Neural nets in the same Indiv

Simply Genetic Algorithm And Neural Network PROJECTS (V2) CONTAINS: Genetic Algorithm Class - Simple and easy to use. + Modified ParasChopra Neural Net by www.paraschopra.com. ----- EXAMPLE PROJECT

/* * Test program to find discrete logarithms using Pollard's lambda method * for catching kangaroos. This algorithm appears to be the best * available for breaking the Diffie-Hellman key

/* * Test program to find discrete logarithms using Pollard's lambda method * for catching kangaroos. This algorithm appears to be the best * available for breaking the Diffie-Hellman key

% make rp structure to be used for passing run % parameters to the run_lms_pred algorithm rp.Nruns = 100; rp.Ndata = 500; rp.mult = 200; rp.verbose = 0; rp.mu = 0.05; rp.a =

function Px = min_norm(x,p,M) %MIN_NORM Frequency estimation using the minimum norm algorithm. %-------- %USAGE Px = min_norm(x,p,M) % % The input sequence x is assumed to consist of p complex %

function Px = music(x,p,M) %MUSIC Frequency estimation using the MUSIC algorithm. %----- %USAGE Px=music(x,p,M) % % The input sequence x is assumed to consist of p complex % exponentials in whit

function [gamma,err] = burg(x,p) %BURG All-pole modeling using the Burg algorithm. %---- %USAGE [gamma,err] = burg(x,p) % % An all-pole of order p is found for the input sequence % x using the

function [h,y] = lms(x,d,delta,N) % LMS Algorithm for Coefficient Adjustment % ---------------------------------------- % [h,y] = lms(x,d,delta,N) % h = estimated FIR filter % y = output

function a = predict_performance(algorithm, algorithm_params, features, targets, region) % Predict the final performance of an algorithm from the learning curves % Inputs: % algorithm