[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: computer-go: abstract info and neural nets
Carl,
I am going to do BFGS first since I have programmed that algorithm not long
ago. Right now, I do not think my computer will have enough memory and CPU
power to do EANN in Xin Yao's way, even if I am going to build a cluster.
One thing bother me is that as EANN can be expressed as an NxN matrix, the
evolutionary objective of NN structure and weight can be combined using a
single objective function. Thus, an optimization algorithm can be
implemented to find (locally) optimized NN. Why should people try to have
EANN in an EA, or EP, or GA's way?
Personally, I believe all optimization methods including E* and G* will only
be able to find local optimization. I did not remember any one has claimed
any algorithm that does find global optimization in a mathematical correct
sense.
Weimin
P.S. I rewrite ForeverBlack from C++ to Java for the convenience of data
structure, and better programming. There are not many computing in playing
game, but, learning is slower.
----- Original Message -----
From: "Staelin, Carl" <staelin@xxxxxxxxxxxxxxxxx>
To: <computer-go@xxxxxxxxxxxxxxxxx>
Sent: Sunday, January 13, 2002 11:27 PM
Subject: RE: computer-go: abstract info and neural nets
Weimin,
Given the size of your networks, I think L-BFGS is
the way to go. I think you will find that you get
much better convergence than with momentum backprop.
If you don't have some L-BFGS code of your own,
here is a pointer to some FORTRAN code:
http://www.ece.nwu.edu/~nocedal/lbfgs.html
You should be able to use f2c to convert it to C,
assuming you are using C.
Cheers,
Carl
_________________________________________________
[(hp)] Carl Staelin
Senior Research Scientist
Hewlett-Packard Laboratories
Technion City
Haifa, 32000
ISRAEL
+972(4)823-1237x221 +972(4)822-0407 fax
staelin@xxxxxxxxxxxxxxxxx
_______http://www.hpl.hp.com/personal/Carl_Staelin_______
> -----Original Message-----
> From: Ran Xiao [mailto:ranxiao@xxxxxxxxxxxxxxxxx]
> Sent: Monday, January 14, 2002 12:01 AM
> To: computer-go@xxxxxxxxxxxxxxxxx
> Subject: Re: computer-go: abstract info and neural nets
>
>
> Carl,
>
> Thank you for all the articles about the NN. They all are
> very interesting
> and helpful. I hope one day I can build an artificial brain
> likes Andrew of
> the movie "Bicentennial Man".
>
> I am using quasi 3-layer NN (a 3-layer NN without sigmoid
> function at the
> output layer). The number of input nodes is 81 for 9x9 board.
> Right now, the
> number of hidden nodes is 160. The number of output node is 1
> which is the
> plausible value [0, 1] for a given board for BLACK played.
>
> For the board evaluation, my philosophy is that if the
> players anticipated
> game correctly, the final score will be score for the first
> move. Thus, if
> we have a correct full board evaluation function, no need to play GO.
>
> The current training method thus is supervised
> quasi-reinforced. I am using
> batch mode with back-propagation momentum-based weights
> modification. I was
> thinking to use limited-memory BFGS.
>
> Weimin
>
> P.S. The following is a game I played with ForeverBlack for the latest
> update of NN weight file. The NN training is still far from
> converge, so
> ForeverBlack behaves different every time I updated its
> weight file. The
> play is very casual. ForeverBlack does not count stones, I
> briefly counted
> it myself.
>
> Date Sun Jan 13 13:07:16 PST 2002
> Boardsize 9
> Handicap 0
> Komi 5.5
> Black ForeverBlack
> White Human
> Score 11 43
> B 0 D5
> W 1 F5
> B 2 E4
> W 3 E6
> B 4 A2
> W 5 F4
> B 6 F7
> W 7 E7
> B 8 B5
> W 9 C7
> B 10 A7
> W 11 E3
> B 12 C6
> W 13 D6
> B 14 D3
> W 15 E2
> B 16 B7
> W 17 C8
> B 18 H7
> W 19 G6
> B 20 F2
> W 21 G2
> B 22 G3
> W 23 F3
> B 24 C2
> W 25 D2
> B 26 D8
> W 27 E8
> B 28 G7
> W 29 H6
> B 30 E9
> W 31 F8
> B 32 D4
> W 33 B8
> B 34 H9
> W 35 G8
> B 36 B3
> W 37 A8
> B 38 H5
> W 39 H4
> B 40 G4
> W 41 J5
> B 42 E1
> W 43 D1
> B 44 B1
> W 45 C1
> B 46 G1
> W 47 F1
> B 48 C9
> W 49 H3
> B 50 D7
> W 51 D9
> B 52 D8
> W 53 F9
> B 54 D7
> W 55 D9
> B 56 D8
> W 57 B9
> B 58 J6
> W 59 G5
> B 60 B6
>
>
>