A note on the complex and bicomplex valued neural networks
This work provides theoretical foundations for neural networks using complex and bicomplex numbers, which is incremental as it extends existing algorithms to new algebraic structures.
The paper tackled the problem of extending the perceptron convergence algorithm to complex and bicomplex multivalued neural networks, resulting in a proof for both cases and other theoretical results based on bicomplex algebra.
In this paper we first write a proof of the perceptron convergence algorithm for the complex multivalued neural networks (CMVNNs). Our primary goal is to formulate and prove the perceptron convergence algorithm for the bicomplex multivalued neural networks (BMVNNs) and other important results in the theory of neural networks based on a bicomplex algebra.