You can learn about the science of ridiculously complicated neural networks
through a free Udacity course from Google,

  https://www.udacity.com/course/deep-learning--ud730

it won't explain alphago's networks but will explain the general
architecture (watts towers?) and the google Tensor Flow toolkit.

I ended up skipping the exercises because of tool problems, but the video
lectures give a pretty good overview of how to build inscrutable computer
programs for several different classes of inscrutability.  The discussion
of how to feed images into deep learning networks probably covers a lot of
the techniques used in alphago.

-- rec --


On Mon, Mar 14, 2016 at 6:52 PM, Russ Abbott <[email protected]> wrote:

> You can get most articles through Sci-Hub
> <https://plus.google.com/u/0/+RussAbbott1/posts/5YGik2SsyDV>. The Nature
> piece is available here
> <http://sci-hub.io/http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html>.
> Amazing!
>
> -- Russ
>
> On Mon, Mar 14, 2016 at 3:38 PM Robert J. Cordingley <
> [email protected]> wrote:
>
>> Access, for a fee, to the original Jan, 2016 Nature article on AlpahGo is
>> at http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html.
>> The freely available abstract says it uses deep neural networks ('value
>> networks' and 'policy networks'), tree search and Monte Carlo algorithms.
>> Figures and tables with more information are also freely available from
>> http://www.nature.com/nature/journal/v529/n7587/fig_tab/nature16961_ft.html
>>
>> Robert C
>>
>>
>> On 3/13/16 8:53 PM, Steve Smith wrote:
>>
>> Me, I'm still stuck in the 80's... most of what I know about GO programs
>> involves trying to solve them using cellular automata systems based on the
>> promise of hardware implementations and other esoteric ways of doing CA
>> computation...   Tomasso Toffolli's custom CA hardware was one promising
>> thing that I think eventually fizzled as was our own Jim Crutchfield's
>> analog "video feedback" CA computing concepts...
>>
>> My own favorite which I went on to do some exploratory work in was the
>> "memoisation" work of Bill Gosper which involves generating hash tables at
>> each scale (say 3x3, 6x6, 12x12, 24x24) cell arrays such that if
>> "redundant" patterns occurred at any scale they could be "looked up"
>> instead of computed.   In a 3x3 (9 cell) array, there are naturally only
>> 512 (2^9) hash indices so the computation at that level is manageable by
>> memoisation... while a 6x6 is 2^36 or roughly 64M entries, not quite so
>> tractable/trivial if the distribution of possible configurations of binary
>> CA were uniform...  which interesting GO configurations naturally are
>> NOT.   A slight modification to this is that a binary CA is not sufficient
>> since the states of each cell can be White/Black/Empty... so the math
>> changes to 4^9 and 4^26,etc...
>>
>> Similar attempts were made for checkers and chess which as I remember,
>> the state space for Checkers is much larger than for Chess (surprising?)
>> but GO... much higher (larger board!) and the depth (number of relevant
>> moves ahead) also much higher!
>>
>> I look forward to hearing what the current state of computer GO play
>> might look like as well!
>>
>> - Steve
>>
>>
>> There were stories during the expert systems episode in the 80's that
>> some experts when debriefed in an attempt to identify their rules went on
>> to lose faith in their own expertise and to resign from the field. Other
>> anecdotes talked about how some experts weren't capable of expressing their
>> expertise - such knowledge, skills & experience was referred to as
>> 'compiled knowledge', accessible but not expressible, much like Artificial
>> Neural Networks are. Work
>> <http://www.sciencedirect.com/science/article/pii/0950705196819204> to
>> address this problem has been underway since the 90's. Perhaps others here
>> can provide an update?
>>
>> Robert C
>>
>> On 3/13/16 8:45 AM, Marcus Daniels wrote:
>>
>> I think a deep neural network trained from self play has a subjective, and 
>> even inscrutable inner representation.  Imagine such techniques were applied 
>> to public policy decisions or medical diagnosis.   Without a linguistic 
>> component that co-evolved to describe a taken action, one could be left with 
>> robot savants that outperformed humans on crucial tasks and no one, 
>> including the robot, would have any idea why.
>>
>> Sent from my iPhone
>>
>>
>> On Mar 13, 2016, at 8:01 AM, Roger Critchlow <[email protected]> <[email protected]> 
>> wrote:
>>
>> I've been watching parts of the match between Lee Sedol and Alpha Go on the 
>> youtube deepmind channel.  It's quite good, they start off with a discussion 
>> of the previous game, give running commentary during the game, and audibly 
>> gasp when the progress of the game shocks them.  The post match press 
>> conferences are not to be missed, either.  It's a completely trump free zone.
>>
>> But you're looking at a full day's work for each game, 6 hours and 17 
>> minutes of video from last night's game which Lee Sedol won.  I was too 
>> tired to stay up and watch so I tuned into youtube this morning and watched 
>> the endgame.
>>
>> Apparently I forwarded past the key move, #78, which a Chinese journalist, 
>> quoting a Chinese commentator, called "a God's move".  Lee Sedol replied 
>> that it was the only move he had at the time, that he had thought it would 
>> be easier to make some profit, but it was quite difficult.
>>
>> So the same play is described as both creative genius and inevitable in the 
>> space of a few sentences.  Glad to know that some things will never change.
>>
>> -- rec --
>>
>>
>> ============================================================
>> FRIAM Applied Complexity Group listserv
>> Meets Fridays 9a-11:30 at cafe at St. John's College
>> to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>>
>> ============================================================
>> FRIAM Applied Complexity Group listserv
>> Meets Fridays 9a-11:30 at cafe at St. John's College
>> to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>>
>>
>> --
>> Cirrillian
>> Web Design & Development
>> Santa Fe, NMhttp://cirrillian.com281-989-6272 (cell)
>> Member Design Corps of Santa Fe
>>
>>
>>
>> ============================================================
>> FRIAM Applied Complexity Group listserv
>> Meets Fridays 9a-11:30 at cafe at St. John's College
>> to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>>
>>
>>
>>
>> ============================================================
>> FRIAM Applied Complexity Group listserv
>> Meets Fridays 9a-11:30 at cafe at St. John's College
>> to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>>
>>
>> --
>> Cirrillian
>> Web Design & Development
>> Santa Fe, NMhttp://cirrillian.com281-989-6272 (cell)
>> Member Design Corps of Santa Fe
>>
>> ============================================================
>> FRIAM Applied Complexity Group listserv
>> Meets Fridays 9a-11:30 at cafe at St. John's College
>> to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>
>
> ============================================================
> FRIAM Applied Complexity Group listserv
> Meets Fridays 9a-11:30 at cafe at St. John's College
> to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>
============================================================
FRIAM Applied Complexity Group listserv
Meets Fridays 9a-11:30 at cafe at St. John's College
to unsubscribe http://redfish.com/mailman/listinfo/friam_redfish.com

Reply via email to