Concept Modeling

So we began working on building our own cognitive neural network models using a simple spreadsheet. We're modeling the ways different patterns and features are mapped and how a neural network model might adapt to learning situations as it gains more data and begins to understand the weights of the feature nodes.

While trying to better understand this, I stumbled upon the concept of Semantic relatedness, algorithms and other means for determining the relative meaning of other words, especially through the distance two words are from each other in meaning. One of the more powerful ways of determining semantic relatedness is through Google distance, how related two words are in terms of google searches. Specifically, one can enumerate this idea by understanding the number of hits for two search terms and the overlap of two terms.

Thus, an equation has been developed for this:


Where M is the number of google pages searched for and f(x) and f(y) the number of hits for the corresponding search terms.

As I look at this kind of model, I wonder if our mind works similarly, in that we do a proverbial Google search and see how related two words or concepts are by the number of "results" (categories) they fall under and make a judgment based on the kind of overlap there is. I think I'll want to explore semantic similarity and related concepts more.