Artificial intelligence network load balancing using Ant Colony Optimisation. Download source code - 791 KB Introduction Ants first evolved around 120 million years ago, took form in over 11,400 different species, and are considered one of the most successful insects due to their highly organised colonies, sometimes consisting of millions of ants. One particular notability of ants is their ability to create "ant streets". Long, bi-directional lanes of single file pathways in which they navigate landscapes in order to reach a destination in optimal time. Computer scientists began researching the behaviour of ants in the early 1990's to discover new routing algorithms.
This article details how ACO can be used to dynamically route traffic efficiently. Background Electronic communication networks can be categorised as either circuit-switched or packet-switched. A number of techniques can be employed to optimise the flow of traffic around a network. One of the issues with network routing (especially in very large networks such as the internet) is adaptability. Classes. Artificial intelligence network load balancing using Ant Colony Optimisation. An Object Oriented Neural Engine | Download an Object Oriented Neural Engine software for free. Fast Artificial Neural Network Library | Download Fast Artificial Neural Network Library software for free.
Back-propagation Neural Net. Download demo project - 4.64 Kb Introduction The class CBackProp encapsulates a feed-forward neural network and a back-propagation algorithm to train it. This article is intended for those who already have some idea about neural networks and back-propagation algorithms. If you are not familiar with these, I suggest going through some material first. Background This is part of an academic project which I worked on during my final semester back in college, for which I needed to find the optimal number and size of hidden layers and learning parameters for different data sets.
It wasn't easy finalizing the data structure for the neural net and getting the back-propagation algorithm to work. Here's a little disclaimer... , and for many steps, there is a lot more reasoning required than I have included, e.g., values that I have chosen for parameters, and the number of layers/the neurons in each layer are for demonstrating the usage and may not be optimal. Neural Network FAQ Using the code where: