• As the premier conference series devoted to promotion of and research into Artificial General Intelligence, this years AGI-20 conference will feature several important events related to furthering OpenCog development. In particular, the conference will feature a workshop on “Next Generation AGI Architectures,” and tutorials on “Probabilistic reasoning and pattern mining using OpenCog” and on “Applied Neural-Symbolic Integration Using OpenCog.” 

    One underlying goal of the Next Generation workshop is to engage in a wide-ranging discussion of use-case and desirable features for future scalable cognitive architectures including OpenCog 2.0. Topics covered will include, but are not limited to, novel models of computations, graph database technologies, inference engines, neural-symbolic systems, probabilistic and logical reasoning integration, and others.  

    The Probabilistic Reasoning and Pattern Mining tutorial will focus on our current investigations, using OpenCog tools, into the biological and longevity domains, and will also feature an overview of our current meta-learning efforts.

    The Applied Neural-Symbolic Integration tutorial will feature some of our recent successes (particularly in the areas of traffic analytics, visual question answering, and home automation) in employing symbolic reasoning over subsymbolic data processed by deep neural networks or domain-specific algorithms.

    Additional details are on the conference website https://agi-conf.org/2020

    This entry was posted on Wednesday, February 12th, 2020 at 4:41 pm and is filed under News. You can follow any responses to this entry through the RSS 2.0 feed. You can skip to the end and leave a response. Pinging is currently not allowed.

    News

    Posted on February 12th, 2020

    Written by matt

    Tags

  • 0 Comments

    Take a look at some of the responses we have had to this article.

  • Leave a Reply

    Let us know what you thought.

  • Name(required):

    Email(required):

    Website:

    Message:

%d bloggers like this: