Node Map Learning, and Other Learning Functions

Now, node map learning is functional, and is capable of learning on it's own. Though, through the trial-and-error-like method of learning, any function that has non-static data could screw up the whole learning process, right? Surely something as constantly changing as another learning function would slow all learning to a crawl, forcing the node map to take many more passes to travel the same distance, right? Well, yes and no. Though this logic is correct, to an extent, it actually would really help the AI.

The best way to think of this is like a business. The AI represents the entire company. The node map is the CEO of that company. Each function you hand the node map is another employee type working under the CEO. The types in this case are not actual employees, but are "job titles" which can be filled by multiple people, or simply not used at all. The CEO's job is to get the business operating as well as possible with only these job titles and no more. The only thing the node map (CEO) is able to do is choose where in the company to put each job title. So when the process first starts, he'll look at things, and make logical guesses; passing data from person to person. The thing about learning algorithms in this: they are adaptable. Employees like this have no special talent in a single field, which is difficult for the company to find them a position, but they can adapt to any position, given enough time. Like a business has managers, and people working below them, and other managers, and even more people working below them, node maps can be nested. All forms of learning algorithms are able to be placed inside of a node map and nested. Though, how these are nested is up to the node map.

As stated above, a potential issue with using functions that operate in a non-static manner are likely to throw off the node map's calculations. This is true, and will always slow down the node map's learning curve. In the example of a business, the CEO is putting different people in positions everywhere, where they function poorly. So it moves them. This repeats, a lot. And because a learning algorithm can only learn if it is not moved from it's current position, the curve only has a change to grow when the node map is focusing another another area, instead of the learning algorithm. When the node map places a learning function higher up in the chain, then if has a less chance of being changed, and thus given a much larger chance to learn and grow.

At this point, all of the functions and learning algorithms, including the main node map, are all attempting to work together in order to master their environment. Each one will often trip over each other, or misread data from each other. But, they are help each other. A single algorithms success significantly improves the success of the others. A single algorithms failures can be patched by the others. It is important to use learning algorithms inside a node map, because of this. It may slow down things at first, (by a lot) but it really speeds things up in the long run, and gives the node map much more flexibility.