PDF] The Method of Steepest Descent for Feedforward Artificial Neural Networks

This paper implements the method of Steepest Descent in single and multilayer feedforward artificial neural networks and calculates the three new update weight equations for taking different activation function in different processing unit separately. In this paper, we implement the method of Steepest Descent in single and multilayer feedforward artificial neural networks. In all previous works, all the update weight equations for single or multilayer feedforward artificial neural networks has been calculated by choosing a single activation function for various processing unit in the network. We, at first, calculate the total error function separately for single and multilayer feedforward artificial neural networks and then calculate the three new update weight equations for taking different activation function in different processing unit separately single and multilayer feedforward artificial neural networks. An example is given to show usefulness of this implementation.

What are Neural Networks?

Understand the Impact of Learning Rate on Neural Network

Feed-forward vs feedback neural networks

Steepest descent method

Mathematics, Free Full-Text

An Introduction To Gradient Descent and Backpropagation In Machine

Mathematics, Free Full-Text

Mathematics, Free Full-Text

Review of deep learning: concepts, CNN architectures, challenges

PDF) Artificial Neural Network (ANN

Wiener-Neural-Network-Based Modeling and Validation of Generalized

Frontiers Learning Without Feedback: Fixed Random Learning

Genetic algorithm-determined deep feedforward neural network

Feed Forward Gradient Descent using Matrix Math

Deep learning Back Propagation Gradient Descent and Chain Rule