Engineering General Intelligence, Part 2

Goertzel, Ben; Pennachin, Cassio; Geisweiller, Nil

doi:10.2991/978-94-6239-030-0

Cited by 18 publications

(7 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The representation of RelEx2Logic rules utilizes OpenCog's Atomspace representation [GPG14b], in which various formal systems are given common expression as weighted, labeled hypergraphs. In the Atomspace representation, both link parses, PLN predicate-logic expressions and type expressions are represented as hypergraphs with particular node and link types, which are reviewed e.g.…”

Section: Relex2logicmentioning

confidence: 99%

“…In the Atomspace representation, both link parses, PLN predicate-logic expressions and type expressions are represented as hypergraphs with particular node and link types, which are reviewed e.g. in [GPG14a,GPG14b] 7 . PLN's truth value objects are then represented as weights on certain nodes and links; and may alternately be represented as hypergraphs themselves (since e.g.…”

Section: Relex2logicmentioning

confidence: 99%

See 1 more Smart Citation

Symbol Grounding via Chaining of Morphisms

Lian¹,

Goertzel²,

Vepstas³

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

A new model of symbol grounding is presented, in which the structures of natural language, logical semantics, perception and action are represented categorically, and symbol grounding is modeled via the composition of morphisms between the relevant categories. This model gives conceptual insight into the fundamentally systematic nature of symbol grounding, and also connects naturally to practical real-world AI systems in current research and commercial use. Specifically, it is argued that the structure of linguistic syntax can be modeled as a certain asymmetric monoidal category, as e.g. implicit in the link grammar formalism; the structure of spatiotemporal relationships and action plans can be modeled similarly using "image grammars" and "action grammars"; and commonsense logical semantic structure can be modeled using dependently-typed lambda calculus with uncertain truth values. Given these formalisms, the grounding of linguistic descriptions in spatiotemporal perceptions and coordinated actions consists of following morphisms from language to logic through to spacetime and body (for comprehension), and vice versa (for generation). The mapping is indicated between the spatial relationships in the Region Connection Calculus and Allen Interval Algebra and corresponding entries in the link grammar syntax parsing dictionary. Further, the abstractions introduced here are shown to naturally model the structures and systems currently being deployed in the context of using the OpenCog cognitive architecture to control Hanson Robotics humanoid robots.

show abstract

Section: Relex2logicmentioning

confidence: 99%

Section: Relex2logicmentioning

confidence: 99%

Symbol Grounding via Chaining of Morphisms

Lian¹,

Goertzel²,

Vepstas³

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This theory also introduced the notion of self-organization as a fundamental property of complex systems that enables simple processes to coordinate themselves through networks of local interactions into the higher level emergent organizations that form the defining properties of life and cognition. A complex system's definition of organisms informs many contemporary approaches for modeling general forms of intelligence in technical and computational systems (Goertzel, Pennachin, & Geisweiller, 2014). Notions of complexity and self-organization also exert a strong impact on the social and economic sciences.…”

Section: Scientific and Philosophical Aspects Of Technologymentioning

confidence: 99%

Untitled

2016

Human Technology

View full text Add to dashboard Cite

Human Technology is an interdisciplinary, scholarly journal publishing innovative, peer-reviewed articles exploring the issues and challenges within human-technology interaction and the human role in all areas of our ICT-infused societies.Human Technology, published by the Agora Center, University of Jyväskylä, is distributed without a charge online. ISSN: 1795-6889 www.humantechnology.jyu.fi Volume 12(2), November 2016, 103-104 103From the Publisher CHANGE IN HUMAN TECHNOLOGY'S PUBLISHER: CONTINUED FOCUS ON OPEN ACCESS HUMAN-TECHNOLOGY RESEARCHThe Human Technology journal will begin a new chapter in its publishing life on January 1, 2017. On that date, the responsibility for publishing the journal will transfer to the new Open Science Center at the University of Jyväskylä, an organization currently in development in which one division will oversee the ongoing support of open access publishing at the university. This change is necessitated by the university's decision to close the Agora Center, the interdisciplinary research unit that initiated and supported the journal from its inception. Despite the Agora Center's focus on the phenomena in contemporary society where humans were impacted or facilitated by technology, its international networks of like-minded colleagues, and its commitment to quality interdisciplinary research, the research unit has been deemed unnecessary in the new university structure. As the university's rector indicated in his public announcement in April 2016, it is his belief that this research should be part of the mission of every faculty of the university, and thus the university as a whole. The rector also indicated that the international, open access journal Human Technology was valuable not only to the university but to the scientific community. We are pleased that the current editor in chief, Dr. Pertti Hurme, has agreed to extend his editorship until we bring in a new editor in chief next year. Our long-serving managing editor, Barbara Crawford, M.A., also will continue with the journal. Our international editorial board also will remain active in their work in advancing the mission of the journal. We do not anticipate that the daily operations of the journal will be affected, and, we hope, will be improved by the journal's inclusion in the publications area of the Open Science Center. We are currently negotiating with the administration of the Open Science Center to establish an interdisciplinary publisher's board to maintain and enhance the scientific expertise so essential for a growing journal. We are confident that this will be achieved and the journal can continue to reach new audiences as authors and readers and to continue to advance research in this essential field of human-technology.At this time, I would like to publically acknowledge the long-term expertise and guidance of Dr. Päivi Fadjukoff, currently the director of planning and development for the Agora Center, who has wisely and graciously overseen the role of the publisher in these last 13 years of our jour...

show abstract

“…There are several agent architectures that could potentially be used for modeling artificial animals, although they were not primarily constructed for this purpose, e.g. OpenCog (Goertzel, Pennachin, and Geisweiller, 2014), AERA (Nivel et al, 2013), MicroPsi (Bach, 2015), and NARS (Hammer, Lofthouse, and Wang, 2016).…”

Section: Introductionmentioning

confidence: 99%

Learning and decision-making in artificial animals

Strannegård

Svangård

Lindström

et al. 2018

Journal of Artificial General Intelligence

View full text Add to dashboard Cite

A computational model for artificial animals (animats) interacting with real or artificial ecosystems is presented. All animats use the same mechanisms for learning and decisionmaking. Each animat has its own set of needs and its own memory structure that undergoes continuous development and constitutes the basis for decision-making. The decision-making mechanism aims at keeping the needs of the animat as satisfied as possible for as long as possible. Reward and punishment are defined in terms of changes to the level of need satisfaction. The learning mechanisms are driven by prediction error relating to reward and punishment and are of two kinds: multi-objective local Q-learning and structural learning that alter the architecture of the memory structures by adding and removing nodes. The animat model has the following key properties: (1) autonomy: it operates in a fully automatic fashion, without any need for interaction with human engineers. In particular, it does not depend on human engineers to provide goals, tasks, or seed knowledge. Still, it can operate either with or without human interaction; (2) generality: it uses the same learning and decision-making mechanisms in all environments, e.g. desert environments and forest environments and for all animats, e.g. frog animats and bee animats; and (3) adequacy: it is able to learn basic forms of animal skills such as eating, drinking, locomotion, and navigation. Eight experiments are presented. The results obtained indicate that (i) dynamic memory structures are strictly more powerful than static; (ii) it is possible to use a fixed generic design to model basic cognitive processes of a wide range of animals and environments; and (iii) the animat framework enables a uniform and gradual approach to AGI, by successively taking on more challenging problems in the form of broader and more complex classes of environments

show abstract

Engineering General Intelligence, Part 2

Cited by 18 publications

References 78 publications

Symbol Grounding via Chaining of Morphisms

Symbol Grounding via Chaining of Morphisms

Untitled

Learning and decision-making in artificial animals

Contact Info

Product

Resources

About