Training bidirectional recurrent neural network architectures with the scaled conjugate gradient algorithm
Christodoulou, Chris C.
Promponas, Vasilis J.
Source25th International Conference on Artificial Neural Networks, ICANN 2016
Google Scholar check
MetadataShow full item record
Predictions on sequential data, when both the upstream and downstream information is important, is a difficult and challenging task. The Bidirectional Recurrent Neural Network (BRNN) architecture has been designed to deal with this class of problems. In this paper, we present the development and implementation of the Scaled Conjugate Gradient (SCG) learning algorithm for BRNN architectures. The model has been tested on the Protein Secondary Structure Prediction (PSSP) and Transmembrane Protein Topology Prediction problems (TMPTP). Our method currently achieves preliminary results close to 73% correct predictions for the PSSP problem and close to 79% for the TMPTP problem, which are expected to increase with larger datasets, external rules, ensemble methods and filtering techniques. Importantly, the SCG algorithm is training the BRNN architecture approximately 3 times faster than the Backpropagation Through Time (BPTT) algorithm. © Springer International Publishing Switzerland 2016.
Showing items related by title, author, creator and subject.
Pattichis, Constantinos S.; Charalambous, Chris; Middleton, Lefkos T. (Publ by IEEE, 1991)The usefulness of artificial neural networks (ANNs) trained with the momentum backpropagation and the conjugate gradient backpropagation (CGBP) learning algorithms in the classification of electromyography (EMG) data has ...
Pattichis, Constantinos S.; Charalambous, Chris; Middleton, Lefkos T. (1995)
Finite Difference Schemes for the Cauchy–Navier Equations of Elasticity with Variable Coefficients Bialecki, B.; Karageorghis, Andreas (2015)We solve the variable coefficient Cauchy–Navier equations of elasticity in the unit square, for Dirichlet and Dirichlet-Neumann boundary conditions, using second order finite difference schemes. The resulting linear systems ...