极限学习机（extreme learning machine）ELM是一种简单易用、有效的单隐层前馈神经网络SLFNs学习算法。2004年由南洋理工大学黄广斌副教授提出。传统的神经网络学习算法（如BP算法）需要人为设置大量的网络训练参数，并且很容易产生局部最优解。极限学习机只需要设置网络的隐层节点个数，在算法执行过程中不需要调整网络的输入权值以及隐元的偏置，并且产生唯一的最优解，因此具有学习速度快且泛化性能好的优点。-ELM extreme learning machine (extreme learning machine) is a simple and easy to use, effective SLFNs single hidden layer feedforward neural network learning algorithm. Put forward by Huang Guangbin at nanyang technological university in 2004. The traditional neural network learning algorithm (BP algorithm) need to be set a large amount of network training parameter, and it s easy to produce the local optimal solution. Extreme learning machine only need to set the number of hidden layer nodes of networks, execution of the algorithm does not need to adjust the network weights of the input and hidden yuan bias, and produce the optimal solution, thus has advantages of fast learning speed and good generalization capability.