This paper presents the full deduction of the quasi-Newton learning methods for complex-valued feedforward neural networks. Since these algorithms yielded better training results for the real-valuedâ€¦ (More)

In this paper, complex-valued convolutional neural networks are presented, by giving the full deduction of the gradient descent algorithm for training this type of networks. The performances ofâ€¦ (More)

2016 18th International Symposium on Symbolic andâ€¦

2016

In this paper, we present the deduction of the Levenberg-Marquardt algorithm for training quaternion-valued feedforward neural networks, using the framework of the HR calculus. Its performances inâ€¦ (More)

This paper introduces Lie algebra-valued feedforward neural networks, for which the inputs, outputs, weights and biases are all from a Lie algebra. This type of networks represents an alternativeâ€¦ (More)

We will propose a new algorithm for finding critical points of cost functions defined on a differential manifold. We will lift the initial cost function to a manifold that can be embedded in aâ€¦ (More)

2014 16th International Symposium on Symbolic andâ€¦

2014

In this paper, enhanced gradient descent learning algorithms for complex-valued feed forward neural networks are proposed. The most known such enhanced algorithms for real-valued neural networks are:â€¦ (More)

2015 17th International Symposium on Symbolic andâ€¦

2015

This paper introduces Lie algebra-valued Hopfield neural networks, for which the states, outputs, weights and thresholds are all from a Lie algebra. This type of networks represents an alternativeâ€¦ (More)