Intelligent Constructive Type Systems

Composite types are sets of strings that identify primitive constructors, i.e. functions that return objects of specific data types that are fundamentally built-in (e.g. integers, strings, bools, etc. in a programming language). Unlike these primitive objects, composite objects can only be formed by interpreters, i.e. functions that return nested objects, i.e. sets with elements that … Continue reading Intelligent Constructive Type Systems


Symbolic Adaptive Intelligence

1. Logic of Knowledge An associative graph is learned over a given set of concepts, acting as a statistical model of relevance between clusters of nearby concepts. Semantic networks are created on top this graph, switching out statistical relationships for logical connectives that represent knowledge symbolically. These semantic networks are modeled using frame-like objects called … Continue reading Symbolic Adaptive Intelligence

Adaptive Tree Learning

1. Spanning Trees Simple trees contain single-valued numerical connections, and are made from minimum spanning trees. complex trees are also MSTs, but contain multi-valued connections that represent categories. While numerical comparisons are simple, requiring basic comparative operators, a category is more difficult. There exists no intrinsic order to a set of things, so one must … Continue reading Adaptive Tree Learning

Intelligent Memory Systems

An intelligent memory system IMS is an adaptive system that receives input from a space and produces a set of objects, or models of the information received from input. This is called framing. When an object is used to frame the input, it is considered active. Active objects are more likely to be used in … Continue reading Intelligent Memory Systems

An approach to logical cognition and rationality in artificial intelligence

1. Philosophical Overview The ability to think logically is what distinguishes man from all other animals. Plato believed that we all are  born with something called a “rational soul”, or some essential property of all human beings that gave us the unique ability to think in logical and abstract ways. The result of possessing a … Continue reading An approach to logical cognition and rationality in artificial intelligence

Constraint-based Hierarchical Pattern Detection

Data is received by the constraint-based hierarchical detection system (CHD) in the form of a two-dimensional grid, where each cell contains a single object that holds information. A system is made of multiple grids, each stacked on top of the previous. Between each pair of adjacent grids lies a system called a mapper. A mapper … Continue reading Constraint-based Hierarchical Pattern Detection

Generative Logical Systems

Project on GitHub 1. Objects and Storage A data store has a capacity which limits the amount of information that it can hold. When the capacity of a store is met, the contents are mapped by a function M(S) to another structure called an object. The store is then free to hold new new information … Continue reading Generative Logical Systems

Self-Motivated Intelligent Agents

1. Introduction 1.1 Agents and Environments An agent-based system is comprised of two main functions, the agent function A(s) and the environment function E(a), where s is an observable state of the environment and a is an action selected by the agent. The input received by each function at any given time is the output … Continue reading Self-Motivated Intelligent Agents

Mathematical Foundations of Knowledge

Overview As intelligent beings, we’re able to interpret constraints that effect our understanding of the spatial, temporal, social, political, and economic world that we inhabit. Our intuitive realization of boundaries, I argue, stems from the built-in neurological mechanism of classification and pattern recognition. In order to frame experiences in a meaningful way, there must be … Continue reading Mathematical Foundations of Knowledge

On Relational Knowledge Representation

Overview In order to effectively represent knowledge so that it may be utilized in future problem-solving, it is necessary to encode relational information beginning at the spatial-temporal dimension and working upward with increasing complexity, such that the relations at higher levels are constructed from those below, with the result being a theoretically infinite hierarchy of … Continue reading On Relational Knowledge Representation