Adaptive gradient descent methods such as Adam, RMSprop, and AdaGrad achieve great success in training deep learning models. These adaptively change the rates, resulting a faster convergence speed. Recent studies have shown their problems include extreme non-convergence issues, well poor generalization. Some enhanced variants been proposed, AMSGrad, AdaBound. However, performances of these alte...

In this paper an adaptive PID controller for Wind Energy Conversion Systems (WECS) has been developed. Theadaptation technique applied to this controller is based on Reinforcement Learning (RL) theory. Nonlinearcharacteristics of wind variations as plant input, wind turbine structure and generator operational behaviordemand for high quality adaptive controller to ensure both robust stability an...

The back propagation (BP) algorithm is a very popular learning approach in multilayer feedforward networks. However, the most serious problems associated with the BP are local minima problem and slow convergence speeds. Over the years, many improvements and modifications of the BP learning algorithm have been reported. In this research, we propose a new modified BP learning algorithm by introdu...

To acquire adaptive behaviors of multiple agents in the unknown environment, several neuro-fuzzy reinforcement learning systems (NFRLSs) have been proposed Kuremoto et al. Meanwhile, to manage the balance between exploration and exploitation in fuzzy reinforcement learning (FRL), an adaptive learning rate (ALR), which adjusting learning rate by considering “fuzzy visit value” of the current sta...

Abstract   Many parameter-tuning algorithms have been proposed for training Fuzzy Wavelet Neural Networks (FWNNs). Absence of appropriate structure, convergence to local optima and low speed in learning algorithms are deficiencies of FWNNs in previous studies. In this paper, a Memetic Algorithm (MA) is introduced to train FWNN for addressing aforementioned learning lacks. Differential Evolution...

This paper studies a monetary model that is standard in all respects except that market participants have incomplete knowledge about the economic structure and employ adaptive learning rules to learn about the economic environment. Market participants also must contend with unannounced regime shifts. Simulation results suggest that the models under adaptive learning, especially constant-gain le...

Chinese keyboard typing is fundamental training at school in Taiwan. For the sake of sharp learning curve, many CAI systems have been used to help teaching and learning. However, these CAI systems highly focus on learning results (say speed, accurate rate, etc) rather than learning pro cess. In this paper, we use adaptive learning strategy and agent-based technology to propose an adaptive Chine...

In this paper an adaptive neuro fuzzy inference system based on interval Gaussian type-2 fuzzy sets in the antecedent part and Gaussian type-1 fuzzy sets as coefficients of linear combination of input variables in the consequent part is presented. The capability of the proposed method (we named ANFIS2) to function approximation and dynamical system identification is shown. The ANFIS2 structure ...

A real time recurrent learning (RTRL) algorithm with an adaptive-learning rate for nonlinear adaptive "lters realised as fully connected recurrent neural networks (RNNs) is derived. The algorithm is obtained by minimising the instantaneous squared error at the output neuron for every time instant while the network is running. The algorithm normalises the learning rate with the L 2 norm of the e...