Artificial neural networks using complex numbers and phase encoded weights
- 10 March 2010
- journal article
- research article
- Published by Optica Publishing Group in Applied Optics
- Vol. 49 (10) , B71-B82
Abstract
The model of a simple perceptron using phase-encoded inputs and complex-valued weights is proposed. The aggregation function, activation function, and learning rule for the proposed neuron are derived and applied to Boolean logic functions and simple computer vision tasks. The complex-valued neuron (CVN) is shown to be superior to traditional perceptrons. An improvement of 135% over the theoretical maximum of 104 linearly separable problems (of three variables) solvable by conventional perceptrons is achieved without additional logic, neuron stages, or higher order terms such as those required in polynomial logic gates. The application of CVN in distortion invariant character recognition and image segmentation is demonstrated. Implementation details are discussed, and the CVN is shown to be very attractive for optical implementation since optical computations are naturally complex. The cost of the CVN is less in all cases than the traditional neuron when implemented optically. Therefore, all the benefits of the CVN can be obtained without additional cost. However, on those implementations dependent on standard serial computers, CVN will be more cost effective only in those applications where its increased power can offset the requirement for additional neurons.Keywords
This publication has 37 references indexed in Scilit:
- Solving the XOR and parity N problems using a single universal binary neuronSoft Computing, 2007
- Multilayer Feedforward Neural Network Based on Multi-valued Neurons (MLMVN) and a Backpropagation Learning AlgorithmSoft Computing, 2006
- Universal Binary and Multi-Valued Neurons paradigm: Conception, learning, applications1997
- Speed of processing in the human visual systemNature, 1996
- Rapid local synchronization of action potentials: toward computation with coupled integrate-and-fire neurons.Proceedings of the National Academy of Sciences, 1995
- Pattern recognition computation using action potential timing for stimulus representationNature, 1995
- Temporal encoding in nervous systems: A rigorous definitionJournal of Computational Neuroscience, 1995
- A universal logic element over the complex fieldCybernetics and Systems Analysis, 1991
- Multi-valued threshold functionsCybernetics and Systems Analysis, 1974
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943