Back-propagation learning algorithms

Luo proposed a kind of neural cluster structure embedded in neural networks. The ANN was based on the error back-propagation learning algorithm. The predictive ability of the neural cluster structure was compared with that of common neural net structures. A comparison of predictability with four neural networks was presented and they were applied to correct for matrix effects in XRF. 

Affolter and Clerc" used the connectivity-based encoded structures as input to a two-layer feed-forward network that was trained by the back-propagation learning algorithm. In these experiments correlation coefficients of up to 0.8 for the prediction and up to 0.99 for the recall were achieved. Figure 8... 

The Back-Propagation Algorithm (BPA) is a supervised learning method for training ANNs, and is one of the most common forms of training techniques. It uses a gradient-descent optimization method, also referred to as the delta rule when applied to feedforward networks. A feedforward network that has employed the delta rule for training, is called a Multi-Layer Perceptron (MLP). 

Artificial neural networks often have a layered structure as shown in Figure 8.2 (b). The first layer is the input layer. The second layer is the hidden layer. The third layer is the output layer. Learning algorithms such as back-propagation that are described in many textbooks on neural networks (Kosko 1992 Rumelhart and McClelland 1986 Zell 1994) may be used to train such networks to compute a desired output for a given input. The networks are trained by adjusting the weights as well as the thresholds. 

Neural network learning algorithms BP = Back-Propagation Delta = Delta Rule QP = Quick-Propagation RP = Rprop ART = Adaptive Resonance Theory, CP = Counter-Propagation. 

---