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

Creative Logic Architecture

The Creative Logic Architecture is an intelligent agent architecture that learns to generate high-level patterns in order to reason and make judgments about the world and its own behavior. The agent creates structures of logic using an internal language resembling computer code, and then executes the code to manipulate the information stored in memory. Statements … Continue reading Creative Logic Architecture

Constraint-Based Type Systems

A constraint-based type system is a method of defining data types in terms of the conditions and requirements that a given value must meet in order to be considered a valid instance of a specific type. Each variable has a set of constraints, a set of weights, and a threshold, along with its value at … Continue reading Constraint-Based Type Systems

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

Higher Cognition of Intelligent Agents

Visual analogy The human brain takes advantage of a spatial system that originally developed for visual cognition and applies higher cognitive functioning to map concepts onto a mental space in the form of a visual analogy. Non-spatial relations between ideas are assigned to connections, replacing their use as an indicator of spatial distance with a […]

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