An evolutionary constructive and pruning algorithm for artificial neural networks and its prediction applications

Optimization of neural network model using modified bat-inspired algorithm

“…An ANN can be taught by training it using on hand cases with inputs and expected outputs. Due to the learning ability and nonlinearity method of ANNs [1], they have been used extensively in many applications of data mining such as classification, associate rule algorithm for ANN training was proposed in [9]. However, most of these strategies need the chromosome length to be predefined.…”

“…In the literature a few number of methods [1,26,29] have been applied for optimizing both weights and structure of neural network simultaneously. It is the significance of the research in this area to find a superior solution for the neural network model.…”

Optimizing the echo state network with a binary particle swarm optimization algorithm

“…Many researchers have recently focused their efforts on new ways to optimize the architecture of artificial neural networks, including the methods of pruning [21,22], construction [23] and evolutionary algorithms [24][25][26]. Constructing algorithms start training with a small network and incrementally add hidden nodes during training when the network cannot reduce the training error.…”

Approximation of phenol concentration using novel hybrid computational intelligence methods

“…In many cases one can achieve much higher performance while the system complexity is only slightly increased (Tallon-Ballesteros and Hervas-Martinez, 2011). The most popular hybrid systems include evolutionary-neural (Font et al, 2010;Chandra et al, 2011;Su et al, 2011;Tong and Schierz, 2011;Yang and Chen, 2012;Zhang et al, 2011), evolutionary-fuzzy (Cheng et al, 2010;Lin and Chen, 2011;Antonelli et al, 2009;Cheshmehgaz et al, 2012;Aydogan et al, 2012) and neuro-fuzzy systems (Shahlaei et al, 2012;Czogała and Łęski, 2000;Tadeusiewicz, 2010b;Tadeusiewicz and Morajda, 2012).…”