go programs
Locked
 
|
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 |
|
|
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 <[hidden email]> 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 |
|
|
In reply to this post by Roger Critchlow-2
Here's the link for match 4 (of 5) that AlphaGo resigned. Score now
stands at 3:1.
https://www.youtube.com/watch?v=yCALyQRN3hw Post match press conference starts around 5:45:10 - a big news event in Korea. Robert C On 3/13/16 8:00 AM, Roger Critchlow
wrote:
-- Cirrillian Web Design & Development Santa Fe, NM http://cirrillian.com 281-989-6272 (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 |
|
|
Then I'm wondering if in losing the first 3 games Lee Sedol was no
longer under any pressure to win the $million prize and could play
in a more relaxed but more focused way - tho' I've not seen any
commentary that effect yet.
Interestingly AlphaGo was initially trained on strong amateur games available on the internet and no Lee Sedol games. It got stronger by playing itself. Wonder what would happen if it trained on available professional games but a few more hundred games wouldn't apparently make much difference since "AlphaGo required millions of games to train itself". FYI the final match 5 is on Monday Mar 14 9:00 pm Mountain Time - Tuesday Mar 15 04:00 GMT Robert C On 3/13/16 9:03 AM, Robert J.
Cordingley wrote:
Here's the link for match 4 (of 5) that AlphaGo resigned. Score now stands at 3:1. -- Cirrillian Web Design & Development Santa Fe, NM http://cirrillian.com 281-989-6272 (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 |
|
|
In reply to this post by Marcus G. Daniels
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
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 iPhoneOn Mar 13, 2016, at 8:01 AM, Roger Critchlow [hidden email] 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, NM http://cirrillian.com 281-989-6272 (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 |
|
|
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 to address this problem has been underway since the 90's. Perhaps others here can provide an update? ============================================================ 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 |
|
|
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:
-- Cirrillian Web Design & Development Santa Fe, NM http://cirrillian.com 281-989-6272 (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 |
|
|
On Mon, Mar 14, 2016 at 3:38 PM Robert J. Cordingley <[hidden email]> wrote:
============================================================ 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 |
|
|
You can learn about the science of ridiculously complicated neural networks through a free Udacity course from Google, 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 <[hidden email]> wrote:
============================================================ 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 |
|
|
I love Go and the mysterious exponential expansion of humans and their creations -- while in 3 hours I just dashed off a methanol missive, my online game for 17 years now... 5 sweeteners harm human cells in vitro -- Armorel Diane van Eyk 2014.10.15 -- check for similar harm from methanol -- made by ADH1 enzyme in 20 human cells into formaldehyde, the WC Monte paradigm: Rich Murray 2016.03.14 http://rmforall.blogspot.com/2016/03/5-sweeteners-harm-human-cells-in-vitro.html Drug Chem Toxicol. 2015;38(3):318-27. doi: 10.3109/01480545.2014.966381. Epub 2014 Oct 15. The effect of five artificial sweeteners on Caco-2, HT-29 and HEK-293 cells. van Eyk AD 1. 1 Division of Pharmacology, Department of Pharmacy and Pharmacology, University of the Witwatersrand , Parktown , South Africa. Taylor & Francis Group Armorel Diane van Eyk ... !! Rich Murray On Mon, Mar 14, 2016 at 5:16 PM, Roger Critchlow <[hidden email]> wrote:
============================================================ 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 |
«
Return to Friam
|
1 view|%1 views
| Free forum by Nabble | Edit this page |