Abstract | ||
---|---|---|
We present a backpropagation learning algorithm for multilayer feedforward phasor neural networks using a gradient descent method. The state of a phasor neuron takes a complex-valued state on the unit circle in the complex domain. Namely, the state can be identified only by its phase component because the amplitude component is fixed. Due to the circularity of the phase variable, phasor neural networks are useful to deal with periodic and multivalued variables. Under the assumption that the weight coefficients are complex numbers and the activation function is a continuous and differentiable function of a phase variable, we derive an iterative learning algorithm to minimize the output error. In each step of the algorithm, the weight coefficients are updated in the gradient descent direction of the error function landscape. The proposed algorithm is numerically tested in function approximation task. The numerical results suggest that the proposed method has a better generalization ability compared with the other backpropagation algorithm based on linear correction rule. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-10677-4_55 | ICONIP (1) |
Keywords | Field | DocType |
complex-valued neuron,gradient descent.,backpropagation learning algorithm,weight coefficient,error function landscape,activation function,phasor neural networks,multilayer phasor neural networks,complex-valued state,backpropagation algorithm,multilayer feedforward phasor neural,learning,function approximation task,proposed algorithm,backpropagation,differentiable function,phase variable,gradient descent method,neural network,gradient descent,function approximation | Stochastic gradient descent,Gradient descent,Feedforward neural network,Computer science,Phasor,Algorithm,Multilayer perceptron,Artificial intelligence,Backpropagation,Artificial neural network,Rprop,Machine learning | Conference |
Citations | PageRank | References |
0 | 0.34 | 8 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gouhei Tanaka | 1 | 51 | 11.80 |
Kazuyuki Aihara | 2 | 1909 | 333.03 |