Abstract:

This study investigates the fluid intelligent capabilities of a layered artificial intelligence in the feed of streaming polymorphic unstructured data. With a data independent design, we are able to find relations between ideas within certain defined topics and the relationship between those ideas. Our algorithm was back tested against the “United States Financial Markets” as a topic with apparent and easily quantifiable relationships. We present a method to simulate multi-layered memory as a means to augment temporal relationships between nodes, define properties of node types without a predefined schema, and find centrality and distribution overlaps between the context sensitive surroundings of each idea node. We then present an in depth analysis into the errors with such a fluid intelligent machines and the simulacra that facilitate its fluid intelligent capabilities.
In a pursuit towards a truly dynamic artificial intelligence, it is necessary to establish a recurrent method to decipher the presence of concrete yet abstract entities (“ideas”)  independent of a related and coherent topic set.
A considerable amount of work venturing into this field has culminated in the prevalence of statistical methods to extract probabilistic models dependent on large amounts of unstructured data. These Bayesian data analytic techniques often result in an understanding superficial in the context of a true relational understanding. Furthermore, this “bag-of-words” approach when looking at amounts of unstructured data (quantifiable by correct relationships derived between the idea nodes) often relate to a single dimensional understanding of the topics at hand. Traditionally, when these topics are transformed, it is difficult to extract hierarchy and queryable relations using matrix transformations from a derived data set
This project is an effort to change the approach from which dynamic fluid intelligence is derived, finding a backbone in streaming big data. Ideally, this model would be able to take a layered, multi-dimensional approach to autonomous identification of properties of dynamically changing ideas from portions of said data set. It would also be able to find types of relationships, ultimately deriving a set of previously undefined relational schemas through unsupervised machine learning techniques that would ultimately allow for a queryable graph with properties and nodes initially undefined.

Advertisements