Thanks Tom, Always great to get some good links to help understand these ideas.
Jeff and several of us were talking about this during the hackathon, too. I have an idea that the CLA gives rise to a process which maximises the structural (spatiotemporal and sensorimotor) information extracted from the data stream and stored in the region. This information content can be equated to the entropy as alluded to in your email. We were discussing the idea that the human brain (and all mammals' too) has a reward mechanism for learning about the world, because it is expensive to do but the long-term benefits outweigh the cost. Jeff mentioned the fact that young men are particularly risk-seeking (ie they take risks in the pursuit of new experiences). This would indicate that evolution considers the gathering of some kinds of experiences as worth the potential death of the organism, which is quite something if you think about it. This would add the "selfish brain" to the idea of the "selfish gene" as well as explaining why people can be so reckless at times. I often feel like learning is addictive, as if I'm receiving an injection of some very pleasant narcotic when I am learning something new and interesting, or when I come up with a solution to a difficult challenge. I'm sure that this is the reward mechanism we were discussing. Regards, Fergal Byrne On Sat, Nov 16, 2013 at 2:14 AM, Thomas Macrina <[email protected]>wrote: > In the office hours on Tuesday, Jeff mentioned there being a potential > approach for system motivation using entropy. That made me look back at an > article that Wissner-Gross & Freer published in April called "Causal > Entropic Forces" that got some press for simulating adaptive behavior. It > very much aligns with what Jeff mentioned, so I figured it'd be worth > sharing. > > For anyone who didn't catch it, here's the > paper<http://math.mit.edu/~freer/papers/PhysRevLett_110-168702.pdf>, > a video of the simulations <http://www.entropica.com/>, and a decent, > less-technical > overview<http://davidruescas.com/2013/04/22/causal-entropy-maximization-and-intelligence/> > . > > The gist: without any guidance, the authors were able to simulate agents > setting and achieving goals, just using a "simple" model that had the > agents moving towards states that afforded them the greatest future > entropy. Or better still, the agents appeared intelligent because they were > putting themselves in positions that gave them the most options. > > If you wanted to take a swing at implementing their model, the meat and > potatoes is in the path integration of equation 11, but I think the > trickiest part could be parametrizing the path temperature. Then it sounds > like you have your agent run Monte Carlo simulations on potential futures > at each timestep (Eron's "Imagine That" hack is ahead of the game). > > It could be a useful motivation engine within NuPIC, somewhere down the > line. It feels like it's a slightly higher abstraction than the current > neuron level, and it would definitely need to make use of the sensor-motor > pathways. Nothing that this community can't handle. > > Tom > > _______________________________________________ > nupic mailing list > [email protected] > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > -- Fergal Byrne, Brenter IT <http://www.examsupport.ie>http://inbits.com - Better Living through Thoughtful Technology e:[email protected] t:+353 83 4214179 Formerly of Adnet [email protected] http://www.adnet.ie
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
