Recursive neural networks

DOMpro Protein Domain Prediction Using Profiles, Secondary Structure, Relative Solvent Accessibility and Recursive Neural Networks. 

Duce C, MicheU A, Starita A et al. (2006) Prediction of polymer properties from their structure by recursive neural networks. Macromol Rapid Commun 27 711-715... 

Bini R, Ciappe C, Duce C, Micheli A, Solaro R, Starita A, Tine MR (2008) Ionic liquids prediction of their melting points by a recursive neural network model. Green Chem 10 306-309... 

Empirical Comparison of Recursive Neural Networks and Tree Kernel Methods on Regression Tasks for Tree Structured Domains. 

A different way of encoding the structure consists of using chemical graphs as input for a recursive neural network (RNN). The RNN automatically encodes the structural information depending on the computational problem at hand. [36] Again, the influence of the anion was overlooked, for this methodology was applied to a set of ILs based on pyridinium bromide. 

Other related approaches are based on the use of neural networks and recursive partitioning [71-74],... 

M. Tajine and D. Elizondo, Neural Networks, 11,1571 (1S>98). The Recursive Deterministic Perceptron Neural Network. 

In order to obtain adequate data estimation for the reaction rates, PRBS input sequences in Fb and Tr were introduced, using a sample time of 1000 sec. Operation conditions and outlet concentrations were register to train the neural networks. The model update that consists of the NN adaptation was carried out using a second order recursive algorithm. The best NN structures were found by a systematic training procedure, considering outlet concentrations of A and B components and the reactor temperature as the inputs to the networks. Finally, networks with one hidden layer with four nodes and sigmoidal activation functions were selected. 

Fig. 1. Pattern recognition methods. ANN, artificial neural networks BP ANN, back-propagation ANN CA, cluster analysis CART, classification and regression trees (recursive partitioning) CCA, canonical correlation analysis CVA, canonical variate analysis kNN, -nearest neighbor methods LDA, linear discriminant analysis PCA, principal component analysis PLS DA, partial least squares regression discriminant analysis SIMCA, soft independent modeling of class analogy SOM, self-organizing maps.

S. Chen, C.F.N. Cowan, S.A. Billings, and P.M. Grant, Parallel Recursive Prediction Error Algorithm for Training Layered Neural Networks , International Journal of control, 51, (6), pp. 1215-1228. 1990. 

Linear f— Neural Regression/ Network PLS —f Recursive SVM —/ Partitioning... 

---