A multi-layer quaternion neural network that conducts its learning using a quaternion back-propagation algorithm is employed to design the facial expression recognition system. The input feature vector of the recognition system is composed of histograms of oriented gradients calculated from an input ...
In particular the book contributed with a new method of ensemble backpropagation learning that takes into account boosting weights, modification of the fuzzy c-means clustering algorithm for ensembles, novel design of the Mamdani, Takagi Sugeno, relational and logical fuzzy systems constituting the ...
Also, a realtime recurrent learning extended to quaternion numbers is introduced to train the network using a back-propagation algorithm. In the computational experiments, a three-link robot manipulator controlled using the proposed QRNN-based controller is used. The simulation results demonstrate the ...
A back-propagation algorithm with an adaptive learning rate is applied for the supervised training of the multi-layer quantum neural network. To evaluate the capability of the learning-type quantum neural control system, computational experiments are conducted for controlling a nonholonomic system - in...
The control system consists of the quaternion neural network, feedforward model and feedback controller, resulting in a feedback error learning scheme utilised for the training of the quaternion neural network with a backpropagation algorithm extended to quaternion numbers. In computational experiments, ...
The authors used synthesised extreme gradient boost algorithms optimised by various meta-heuristic optimisation algorithms, including the reptile search algorithm, aquila optimiser, and arithmetic optimisation algorithm. Seven input properties were chosen as the predictors of the carbonation depth of RAC: ...