I’m thinking. About the ALPHA GO thing.
Go has how many possible actions? Couldn’t that be converted into a Markov chain? Is a Markov chain even the thing I really want (I’m unsure If it’s deterministic 100%, since it involves greedy randomness). Do you follow the overall idea tho? Love the responses so far PAIN.IQ(0) LG > On 5. Aug 2019, at 19:59, [email protected] wrote: > > woah, now were going crazy! > I didnt mean that much, all i meant was about a 5 letter input (a-z)-5 > nuerons a lettah, mesh to about 5 neurons*1 meg internal patterns to give me > a 1 letter output (a-z) 5 neurons a lettah, get your redskin. > Get a good near match on this sucker, probably start responding half > correctly after the 10th pattern goes into it.. cause of good old k nearest > neighbour in action! d=D > Artificial General Intelligence List <https://agi.topicbox.com/latest> / AGI > / see discussions <https://agi.topicbox.com/groups/agi> + participants > <https://agi.topicbox.com/groups/agi/members> + delivery options > <https://agi.topicbox.com/groups/agi/subscription>Permalink > <https://agi.topicbox.com/groups/agi/Tc76caae243407ce2-Mb0528d24e7cc33769c37ecb3> ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tc76caae243407ce2-M1769d24434150986fa0c2891 Delivery options: https://agi.topicbox.com/groups/agi/subscription
