Category Archives: Theory

Symbolic and Neural Nets: Two Sides of the Same Coin

Posted on October 21, 2018 by Linas Vepstas

Deep learning and neural nets are all the rage, today, and have displaced symbolic AI systems in most applications. It’s commonly believed that the two approaches have nothing to do with each other; that they’re just completely different, and that’s … Continue reading →

Posted in Theory | Tagged , , , , , , , | 1 Comment

Medieval Thinking and Political AGI

Posted on May 27, 2018 by Linas Vepstas

A cherry picked quote from a review of a new book: “In his new book, Pearl, now 81, elaborates a vision for how truly intelligent machines would think. The key, he argues, is to replace reasoning by association with causal … Continue reading →

Posted in Meta, Theory, Uncategorized | Tagged , | 1 Comment

Inference Meta-Learning (part I)

Posted on October 14, 2017 by nilg

This is the introductory part of a blog series about my work on inference control learning for OpenCog. It introduces the problematic, an initial design solution and some early results. More interesting results will come in subsequent parts. Introduction Inference … Continue reading →

Posted in Development, Theory | 3 Comments

Smart Contract Blockchains

Posted on October 18, 2016 by Linas Vepstas

Blockchains and smart contracts are all the rage, these days. What does this have to do with OpenCog?  Let me explain. TL;DR: The idea of a block-chain comes from the idea of block ciphers, where you want to securely sign … Continue reading →

Posted in Design, Theory, Uncategorized | 2 Comments

Many Worlds: Reasoning about Reasoning

Posted on August 31, 2016 by Linas Vepstas

When one reasons about the world, what is one actually doing? This post is about that. Its also about some abstract nonsense. Continue reading →

Posted in Design, Development, Theory | 8 Comments