Banner
2014: Postmortem

Oh no! I forgot to post a personal postmortem1 for the year 2014 like I did for the previous year...

Cognitive Abstraction Manifolds

A few days ago I started thinking about abstractions whilst reading Surfaces and Essences, a recent...

On That Which is Called “Memory”

Information itself is a foundational concept for cognitive science theories.But the very definition...

Polymorphism in Mental Development

Adaptability and uninterrupted continuous operations are important features of mental development...

User picture.
picture for Hank Campbellpicture for Helen Barrattpicture for Ladislav Kocbachpicture for Sascha Vongehrpicture for Bente Lilja Byepicture for Steve Schuler
Samuel KenyonRSS Feed of this column.

Robotics software engineer, AI researcher, interaction designer (IxD). Also (as Sam Vanivray) filmmaker, actor.

Working on my new sci-fi movie to be filmed in 2016:
BRUTE SANITY... Read More »

Blogroll
My short paper, "An Ecological Development Abstraction for Artificial Intelligence," will be featured in the symposium "How Should Intelligence be Abstracted in AI Research: MDPs, Symbolic Representations, Artificial Neural Networks, or _____?" and will be published in the AAAI (Association for the Advancement of Artificial Intelligence) technical report for the AAAI 2013 Fall Symposium Series. The symposia will occur November 15-17 in Arlington, Virginia.This is the abstract:
A biologically inspired AI abstraction based on phylogenetic and ontogenetic development is proposed.
I'm working on some ideas and a paper to present my version of biologically-inspired development. But not just as a single project or as a technique, but as an abstraction level.

It's hard to explain, so let me first digress with this: The agent approach to AI became a mainstream part of AI in the 1990s, and one of the most popular AI textbooks of the past decade tries to frame all of AI in the context of agents. Certainly within a given project, one can refer to the agent layer of abstraction. But I wonder how much agent as abstraction actually matters.
Cognition causes language, not the other way around. Correlations between changes in thought with changes in language abound. But the arguments are very weak for causality from language to cognition in this context.

What do People Mean by Language Shapes Thought?



Lera Boroditsky likes to spread the meme language shapes thought. Others have used it too when talking about Whorfian matters.
Philosopher Aaron Sloman claims that symbol grounding is impossible. I say it is possible, indeed necessary, for strong AI. Yet my own approach may be compatible with Sloman's.

Sloman equates "symbol grounding" with concept empiricism, thus rendering it impossible. However, I don't see the need to equate all symbol grounding to concept empiricism. And what Sloman calls "symbol tethering" may be what I call "symbol grounding," or at least a type of symbol grounding.

Firstly, as Sloman says about concept empiricism [1]:
Kant refuted this in 1781, roughly by arguing that experience without prior concepts (e.g. of space, time, ordering, causation) is impossible.
What if I told you that fictional mysteries contain practical real-world methodologies? I have pointed out the similarities between detectives solving mysteries to software debugging before. My day job of writing code often involves fixing bugs or solving bizarre cases of bad behavior in complex systems.

In a new book called Mastermind: How to Think Like Sherlock Holmes, Maria Konnikova also compares the mental approaches of a detective to non-detective thinking [1].
Since I didn't blog in back in 2004, you get to suffer--I mean, enjoy--another breathtaking misadventure down memory lane.

In 2004 I started designing and coding (in C++) a cognitive architecture called Biomimetic Emotional Learning Agents (BELA).

The Grand Plan


This antique diagram reveals my old plans:



The diagram indicates general flow of time from left to right, but the arrows primarily show development paths. Useful developments to the primary tree could come from any position vertically.