• Corpus ID: 18117757

OpenCog: A Software Framework for Integrative Artificial General Intelligence

  title={OpenCog: A Software Framework for Integrative Artificial General Intelligence},
  author={David Hart and Ben Goertzel},
The OpenCog software development framework, for advancement of the development and testing of powerful and responsible integrative AGI, is described. The OpenCog Framework (OCF) 1.0, to be released in 2008 under the GPLv2, is comprised of a collection of portable libraries for OpenCog applications, plus an initial collection of cognitive algorithms that operate within the OpenCog framework. The OCF libraries include a flexible knowledge representation embodied in a scalable knowledge store, a… 
OpenCogPrime: A cognitive synergy based architecture for artificial general intelligence
  • B. Goertzel
  • Computer Science
    2009 8th IEEE International Conference on Cognitive Informatics
  • 2009
The key aspects of OCP are described here in the context of the theoretical foundation of “cognitive synergy theory”; and the current implementation status is briefly reviewed.
CogPrime : An Integrative Architecture for Embodied Artificial General Intelligence
The CogPrime architecture for embodied AGI is overviewed, covering the core architecture and algorithms, the underlying conceptual motivations, and the emergent structures, dynamics and
Industrialization of Customized AI Techniques: A Long Way to Success!
Implementing and integrating a complex artificial intelligence (AI) powered system into industrial production is a long way to go. Even if there is already a working system in the lab, there is a
My title
Research in Artificial Intelligence (AI) has focused mostly on two extremes: either on small improvements in narrow AI domains, or on universal theoretical frameworks which are usually uncomputable,
ToyArchitecture: Unsupervised Learning of Interpretable Models of the World
This work presents a novel, purposely simple, and interpretable hierarchical architecture which combines multiple different mechanisms into one system: unsupervised learning of a model of the world, learning the influence of one’s own actions on theworld, model-based reinforcement learning, hierarchical planning and plan execution, and symbolic/sub-symbolic integration in general.
Implementation of graph database for OpenCog artificial general intelligence framework using Neo4j
The GraphBackingStore API extends the current BackingStore C++ API and can take special queries that map naturally into Cypher queries and simple manipulations of Neo4j graph traversals.
Community driven artificial intelligence development for robotics
This PhD research attempts to create a special online community for building a new artificial intelligence (AI) software for Sony ERS-7 robots as a case study to explore new ways of modern AI development.
Cognitive Bias for Universal Algorithmic Intelligence
The way to the real AGI consists in bridging the gap between these two approaches, if one considers cognitive functions as a "cognitive bias" that should be incorporated into the models of universal algorithms without violating their universality.
Towards learning 2.0
A special focus is given on the attempt to draw lessons from a detailed study of evolutionary and developmental processes and stages of learning in nature, in particular in human beings, and a number of principles for machine learning are inferred.
General Attention Mechanism for Artificial Intelligence Systems
In the domain of intelligent systems, the management of mental resources is typically called “attention”. Attention exists because all moderately complex environments – and the real-world


NOVAMENTE: An Integrative Architecture for Artificial General Intelligence
Novamente integrates aspects of many prior AI projects and paradigms, including symbolic, neural-network, evolutionary programming and reinforcement learning approaches; but its overall architecture is unique, drawing on system-theoretic ideas regarding complex mental dynamics and associated emergent patterns.
Toward social mechanisms of android science
Toward Social Mechanisms of Android Science was the first workshop at which researchers from various disciplines joined to discuss the application of very humanlike robots to the study of interaction
The Prehistory of the Mind
Mithen begins his book by first posing and then answering the question, OWhy ask an archaeologist about the human mind?O As he describes, there are many fields of study that can contribute to the
Exploring Android Developmental Psychology in a Simulation World
A research programme oriented toward exploring the development of android cognition in the context of a 3D simulation world is described. The simulation world itself, AGISim, is an open-source
Cognitive Neuroscience. W.W. Norton
  • Cognitive Neuroscience. W.W. Norton
  • 2002