一、神经网络-支持向量机
支持向量机(Support Vector Machine)是Cortes和Vapnik于1995年首先提出的，它在解决小样本、非线性及高维模式识别中表现出许多特有的优势，并能够推广应用到函数拟合等其他机器学习问题中。 1 数学部分 1.1 二维空间 2 算法部分
二、狮群算法
三、代码
%_________________________________________________________________________%%狮群算法 %%_________________________________________________________________________%function [Best_pos,Best_score,curve]=LSO(pop,Max_iter,lb,ub,dim,fobj)beta = 0.5;%成年狮所占比列Nc = round(pop*beta);%成年狮数量Np = pop-Nc;%幼师数量if(max(size(ub)) == 1)ub = ub.*ones(1,dim);lb = lb.*ones(1,dim); end%种群初始化X0=initialization(pop,dim,ub,lb);X = X0;%计算初始适应度值fitness = zeros(1,pop);for i = 1:popfitness(i) = fobj(X(i,:));end[value, index]= min(fitness);%找最小值GBestF = value;%全局最优适应度值GBestX = X(index,:);%全局最优位置curve=zeros(1,Max_iter);XhisBest = X;fithisBest = fitness;indexBest = index; gbest = GBestX;for t = 1: Max_iter%母狮移动范围扰动因子计算stepf = 0.1*(mean(ub) - mean(lb));alphaf = stepf*exp(-30*t/Max_iter)^10;%幼狮移动范围扰动因子计算alpha = (Max_iter - t)/Max_iter;%母狮位置更新for i = 1:Ncindex = i;while(index == i)index = randi(Nc);%随机挑选一只母狮endX(i,:) = (X(i,:) + X(index,:)).*(1 + alphaf.*randn())./2;end%幼师位置更新for i = Nc+1:popq=rand;if q<=1/3X(i,:) = (gbest + XhisBest(i,:)).*( 1 + alpha.*randn())/2;elseif q>1/3&&q<2/3indexT = i;while indexT == iindexT = randi(Nc) + pop - Nc;%随机位置endX(i,:) = (X(indexT,:) + XhisBest(i,:)).*( 1 + alpha.*randn())/2;elsegbestT = ub + lb - gbest;X(i,:) = (gbestT + XhisBest(i,:)).*( 1 + alpha.*randn())/2; endend %边界控制for j = 1:popfor a = 1: dimif(X(j,a)>ub)X(j,a) =ub(a);endif(X(j,a)<lb)X(j,a) =lb(a);endendend %计算适应度值for j=1:popfitness(j) = fobj(X(j,:));endfor j = 1:popif(fitness(j)<fithisBest(j))XhisBest(j,:) = X(j,:);fithisBest(j) = fitness(j);endif(fitness(j) < GBestF)GBestF = fitness(j);GBestX = X(j,:); indexBest = j;endend%% 狮王更新Temp = gbest.*(1 + randn().*abs(XhisBest(indexBest,:) - gbest));Temp(Temp>ub)=ub(Temp>ub);Temp(Temp<lb) = lb(Temp<lb);fitTemp = fobj(Temp);if(fitTemp<GBestF)GBestF =fitTemp;GBestX = Temp;X(indexBest,:)=Temp;fitness(indexBest) = fitTemp;end[value, index]= min(fitness);%找最小值gbest = X(index,:);%当前代，种群最优值curve(t) = GBestF;endBest_pos = GBestX;Best_score = curve(end);end
5.参考文献：
书籍《MATLAB神经网络43个案例分析》
