Human memory, computer memory, and Memento
June 6, 2012
John Laird, the John L. Tishman Professor of Engineering at the University of Michigan, who has written a new book — The Soar Cognitive Architecture, on Soar (state, operator, and result) a general problem solver — is featured in IEEE Spectrum’s “Techwise Conversations.”
Excerpts from the interview:
In traditional rule-based systems, there’s not this chance to bring in additional knowledge to decide what to do next; it’s really just matching on the conditions. And what we wanted to do was make it more flexible so that you could have knowledge that would impact the selection of the next thing to do.
So, one of [the] things we’ve done recently is adding more memories to Soar so that it can not just look at rules to determine what next, but it can go and access these other memories as well that provide additional information about what to do next. …
What the [Memento] movie did for me was show, here’s a human who doesn’t have this ability [to consolidate short-term memory into long-term memory] that none of our AI systems have, and he’s a cognitive cripple. And he has to do all these things with his body or notes in order to try to survive in the world.
And how can I expect to create an AI system that has the capabilities of humans when I’m missing this key component of human-level cognition, which is episodic memory. …
Having a system that can use lots and lots of what we call “domain knowledge” is going to be critical for the success of these systems. And there’s another research project that’s been going on as long as Soar called Cyc where the goal was to encode lots of very specific—well, a combination of general and specific knowledge. And I think both Cyc and Watson are examples sort of the other side of what you need in order to get intelligence. …
One of the projects we’re working on is to teach robots new tasks and new language through interaction with a human. So that’s an area where we’ll see a lot of growth in the future.