Highly connected dynamic artificial neural networks

TL;DR

This paper introduces a flexible, object-oriented approach to designing artificial neural networks that are highly interconnected and dynamically adaptable, allowing easy modification of structure and activation functions.

Contribution

It presents a novel object-oriented framework for highly connected, dynamic neural networks with customizable activation functions and straightforward structural modifications.

Findings

Supports edges between any layers for high connectivity

Enables dynamic insertion and deletion of nodes, edges, and layers

Provides methods for feedforward, backpropagation, and network management

Abstract

An object-oriented approach to implementing artificial neural networks is introduced in this article. The networks obtained in this way are highly connected in that they admit edges between nodes in any layers of the network, and dynamic, in that the insertion, or deletion, of nodes, edges or layers of nodes can be effected in a straightforward way. In addition, the activation functions of nodes need not be uniform within layers, and can also be changed within individual nodes. Methods for implementing the feedforward step and the backpropagation technique in such networks are presented here. Methods for creating networks, for implementing the various dynamic properties and for saving and recreating networks are also described.