A Predictive Unsupervised Neural Network w/ Spike-Timing Dependent Plasticity

A spike-timing dependent plasticity (STDP) network is a neural network that uses unsupervised learning to build a predictive model of the world. The learning algorithm that adjusts the weights in an STDP network is an online iterative algorithm that functions as a sort of expectation-maximization process. For each neuron in a network, the elapsed time …

Concurrent Learning Mechanisms to Boost Higher Intelligence

Different methods of learning are used to shape the many layers of the brain. This is not the way that standard applications of artificial intelligence seemingly modeled after the brain work, however. In almost all cases, the learning algorithms used today exhibit one or two basic processes that are capable of dealing with specific problems, …

A Path to Higher Intelligence through Mental Modeling

Describing states and events sufficiently is a problem overcome by all existing intelligent beings, and will be faced by all of those to come in the future. States, put simply, are collections of features arranged in a certain way that are used to describe potential configurations of the observable world. In biological systems, features originate …

Drive, Intelligence, and Suffering

an affordance is an awareness of one’s environment with respect to goals that are currently driving behavior and the actions that are currently possible to perform. one recognizes affordances by predicting the effects of actions in the current environment and making judgements based on the desired trajectories corresponding to goals and the expected trajectories of …

Foundations of Neural Systems

1. Introduction and Thesis Neural systems are complex adaptive systems that are designed around the functional and structural properties observed in the mind, particular the human mind. The organizational principles behind their designs are based on observations within biological, neurological and psychological frameworks. The goal of constructing such systems is to produce applicable machines that …

An Intelligent Agent that Builds High-Level Models to Maximize Fitness

the following lays out a framework for an adaptive decision-making agent that constructs models of the world to behave intelligently and maximize its fitness. models and decisions models are structures that represent situational and behavioral patterns. actions that lead to changes in an environment are equivalent to state transitions or paths between differing scenarios. decision-making …

Power in Systems of Intelligent Agents

Intelligent agents are autonomous agents that interact through fundamental communication procedures called protocols. A protocol facilitates message passing between two or more agents within a society, allowing knowledge to flow and diffuse between members. Knowledge acts as the fundamental currency of power within a social system, as one can apply knowledge in the pursuit of …

On Logical Decision-Making

a template constraint is a proposition function that determines whether a given value can be assigned to a variable. a constraint function is a conjunction that takes a set of boolean inputs produced by propositions over a given value, and returns a truth value that indicates whether those propositions hold true. every proposition must be …

Evolutionary-Linguistic Approach to Logical Thought and Behavior

linguistic abilities Without knowing it, your mind is constantly generating tree-like structures of data to represent knowledge. This especially apparent when analyzing sentences and paying attention to how your conception of the ideas being presented develop as the speaker fills you in more and more over time, eventually reaching the point at which you have …