A brief history
The OpenCog system is predominately a free and open source software rewrite of the Novamente Cognition Engine (the NCE), as envisioned by its chief architect Ben Goertzel. As such, many of the papers listed below refer to the NCE in its previous stages of development. OpenCog is supported in part by Novamente LLC and, as such, many OpenCog contributors still have access to the NCE implementation. OpenCog will likely remain similar to NCE for some time, so the papers listed below are today the best available documentation of the future OpenCog system (as well as being generally interesting!)
What to read first
With the exception of some of the review papers it references, the best paper to read first is Virtual Easter Egg Hunting: A Thought- Experiment in Embodied Social Learning, Cognitive Process Integration, and the Dynamic Emergence of the Self. Although it is long, it goes into detail of how the different parts of the system fit together, what they are for, and how they will eventually result in an intelligent system capable of participating in a complex task.
General2008 OpenCog: A Software Framework for Integrative Artificial General Intelligence
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 cognitive process scheduler, and a plug-in architecture for allowing interaction between cognitive, perceptual, and control algorithms.
Note: Building Better Minds will be a much better general explanation of OpenCog and PLN. The PLN book is sort of an appendix to Building Better Minds, explaining a few technical points in more detail.
This book describes Probabilistic Logic Networks (PLN), a novel conceptual, mathematical and computational approach to uncertain inference. In order to carry out effective reasoning in real-world circumstances, AI software must robustly handle uncertainty. However, previous approaches to uncertain inference do not have the breadth of scope required to provide an integrated treatment of the disparate forms of cognitively critical uncertainty as they manifest themselves within the various forms of pragmatic inference. Going beyond prior probabilistic approaches to uncertain inference, PLN is able to encompass within uncertain logic such ideas as induction, abduction, analogy, fuzziness and speculation, and reasoning about time and causality. The book reviews the conceptual and mathematical foundations of PLN, giving the specific algebra involved in each type of inference encompassed within PLN. Inference control and the integration of inference with other cognitive faculties are also briefly discussed.
To understand PLN conceptually, you should also look at the following:
- File:PLN Agents matt v5.pdf which gives a brief summary overview of PLN, without much depth but covering the main features [this was turned into a chapter in BBM]
- The PLN book errata page
- The detailed inference trails in the final part of the Real World Reasoning book, http://goertzel.org/RWR.pdf
- This paper, which gives a better explanation of the semantics of PLN intension and quantifiers in terms of possible worlds semantics: agi-conf.org/2010/wp-content/uploads/2009/06/paper_55.pdf [this was also turned into a chapter in BBM]
- This paper on spatio-temporal reasoning: File:SpatioTemporalReasoning v4.pdf
Related publications pre-dating OpenCog
HiddenPattern2006 The Hidden Pattern: A Patternist Philosophy of Mind
The Hidden Pattern presents a novel philosophy of mind, intended to form a coherent conceptual framework within which it is possible to understand the diverse aspects of mind and intelligence in a unified way. The central concept of the philosophy presented is the concept of "pattern": minds and the world they live in and co-create are viewed as patterned systems of patterns, evolving over time, and various aspects of subjective experience and individual and social intelligence are analyzed in detail in this light.
Papers2007 Virtual Easter Egg Hunting: A Thought- Experiment in Embodied Social Learning, Cognitive Process Integration, and the Dynamic Emergence of the Self (aka The Fundamental Dynamics and Emergent Structures of Cognition)
2006 Patterns, Hypergraphs and Embodied General Intelligence
The Novamente Cognition Engine (NCE) architecture for Artificial General Intelligence is briefly reviewed, with a focus on exploring how the various cognitive processes involved in the architecture are intended to cooperate in carrying out moderately complex tasks involving controlling an agent embodied in the AGI-Sim 3D simulation world. A handful of previous conference papers have reviewed the overall architecture of the NCE, and discussed some accomplishments of the current, as yet incomplete version of the system; this paper is more speculative and focuses on the intended behaviors of the NCE once the implementation of all its major cognitive processes is complete. The “iterated Easter Egg Hunt” scenario is introduced and used as a running example throughout, due to its combination of perceptual, physical-action, social and self- modeling aspects. To aid in explaining the intended behavior of the NCE, a systematic typology of NCE cognitive processes is introduced. Cognitive processes are typologized as global, operational or focused; and, the focused processes are more specifically categorized as either forward-synthesis or backward-synthesis processes. The typical dynamics of focused cognition is then modeled as an ongoing oscillation between forward and backward synthesis processes, with critical emergent structures such as self and consciousness arising as attractors of this oscillatory dynamic. The emergence of models of self and others from this oscillatory dynamic is reviewed, along with other aspects of cognitive-process integration in the NCE, in the context of the iterated Easter Egg Hunt scenario.
2006 Using Dependency Parsing and Probabilistic Inference to Extract Relationships between Genes, Proteins and Malignancies Implicit Among Multiple Biomedical Research Abstracts
It is proposed that the creation of Artificial General Intelligence (AGI) at the human level and ultimately beyond is a problem addressable via integrating computer science algorithms and data structures within a cognitive architecture oriented toward experiential learning. A general conceptual framework for AGI is presented, beginning with a philosophy of mind based on the concept of pattern, then moving to a general mathematical and conceptual framework for modeling intelligent systems (SMEPH = Self-Modifying Evolving Probabilistic Hypergraphs), and finally to an overview of a specific design for AGI, the Novamente AI Engine. The problem of teaching an AGI system is discussed, in the context of Novamente’s embodiment in the AGI-SIM simulation world. An educational program based loosely on Piaget’s developmental stages is outlined, followed by more detailed consideration of the learning by Novamente in AGI-SIM of the Piagetan infant-level capability of “object permanence.”
2005 A Comparison of the Novamente AI Design with the Human Mind/Brain
We describe BioLiterate, a prototype software system which infers relationships involving relationships between genes, proteins and malignancies from research abstracts, and has initially been tested in the domain of the molecular genetics of oncology. The architecture uses a natural language processing module to extract entities, dependencies and simple semantic relationships from texts, and then feeds these features into a probabilistic reasoning module which combines the semantic relationships extracted by the NLP module to form new semantic relationships. One application of this system is the discovery of relationships that are not contained in any individual abstract but are implicit in the combined knowledge contained in two or more abstracts.
2004 NOVAMENTE: An Integrative Architecture for Artificial General Intelligence
This is an overview paper.. but it contains the best account of the different nodes and link types in the Novamente Cognition Engine.
The Novamente AI Engine, a novel AI software
system, is briefly reviewed. Unlike the majority of contemporary AI projects, Novamente is aimed at artificial general intelligence, rather than being restricted by design to one particular application domain, or to a narrow range of cognitive functions. 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 associatedemergent patterns.