Author Archives: Linas Vepstas

About Linas Vepstas

Computer Science Researcher - Hanson Robotics

Text Attribution with Link Grammar

A question was recently asked as to whether Link Grammar could be used to attribute text to a specific author. I had fun writing the reply; let me reproduce it below. It starts at square one. Consider a police detective … Continue reading

Posted in Theory, Uncategorized | Tagged , | Leave a comment

“Wave function collapse” for procedural generation

I’ve just been notified about an exciting and important algorithm for procedural generation: the “wave function collapse algorithm“, described by Marian Kleineberg in 2019. I want to talk about it here, from the viewpoint of natural language generation. It’s a … Continue reading

Posted in Design, Theory, Uncategorized | Leave a comment

Everything is a Network

The goal of AGI is to create a thinking machine, a thinking organism, an algorithmic means of knowledge representation, knowledge discovery and self-expression. There are two conventional approaches to this endeavor. One is the ad hoc assembly of assorted technology … Continue reading

Posted in Theory, Uncategorized | 2 Comments

COVID-19 Modelling and Random Social Networks

Seems like everyone wants to be an epidemiologist these days, so why not OpenCog? After all, diseases spread through networks, propagating from one node to the next. A network is a graph, the AtomSpace is a graph database, and the … Continue reading

Posted in Design, Development, Documentation, Introduction, Theory | Leave a comment

Value Flows

Graphs and graphical databases are now accepted as a very good (the best?) way of capturing the relationship between things. Yet, many of the “things” represented graphically are actually processes.  An example might be the water cycle in nature: rain … Continue reading

Posted in Documentation, Introduction, Theory | Tagged , | 2 Comments