Link-bait title aside he's not wrong, but misses the bigger picture. The key is Salience. What do I mean by that? A mechanism by which we can represent what is important.
Something that causes pain has high salience, whereas a dull patch of wall has low salience. In a biological entity, things that hurt, feed, and arouse are innately salient. That innateness comes from billions of years of evolution selecting for some basic neural and motor pathways. What's salient to a computer intelligent might be completely different, but to make decisions, to exert attention, to learn from reinforcement and punishment, there are some basic systems that need to be in place. The author seems to understand that even if dismissing the whole for a lack of a few parts is silly. Hence my thesis that we should try building embodied intelligence with needs, goals, etc, to use all the rest of what biology has taught us in implementing these other features. On Oct 3, 2013 2:59 PM, "Matthew Taylor" <[email protected]> wrote: > > http://opaqueparcels.com/2013/09/30/the-brain-as-a-model-for-computers-why-jeff-hawkins-wont-lead-us-significantly-closer-intelligent-machines/ > > Any comments? ;-) > > --------- > Matt Taylor > OS Community Flag-Bearer > Numenta > > _______________________________________________ > nupic mailing list > [email protected] > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
