An Efficient Optimization Method for Extreme Learning Machine Using Artificial Bee Colony

Traditional learning algorithms with gradient descent based technique, such as back-propagation (BP) and its variant Levenberg-Marquardt (LM) have been widely used in the training of multilayer feedforward neural networks. The gradient descent based algorithm may converge usually slower than required time in training, since many iterative learning step are needed by such learning algorithm, and difficult setting of learning parameters such as stopping criteria, learning rate, learning epochs, which make it easily cause the over-fitting or trap in local minimum. Moreover, the activation functions adopted in these gradient descent based tuning methods need to be differentiable