From 927491ef0d6443f732a65aa4d1da57f670c06d49 Mon Sep 17 00:00:00 2001 From: "B. Bogart" Date: Wed, 12 Aug 2009 17:06:48 +0000 Subject: Changed "example" (this should be a help-file?) to reflect addition of "rinit" method to set weights to time-seeded random values. svn path=/trunk/externals/ann/; revision=11900 --- examples/ann_som/ann_som.pd | 138 +++++++++++++++++++++++++++----------------- 1 file changed, 84 insertions(+), 54 deletions(-) diff --git a/examples/ann_som/ann_som.pd b/examples/ann_som/ann_som.pd index 9f03979..3d471ed 100644 --- a/examples/ann_som/ann_som.pd +++ b/examples/ann_som/ann_som.pd @@ -1,62 +1,83 @@ -#N canvas 50 -127 640 687 10; -#X msg 131 495 print; -#X msg 132 528 new 5 8 8; -#X msg 127 99 init; -#X msg 128 274 train; -#X msg 129 296 test; -#X msg 128 387 write; -#X obj 70 559 ann_som 4 9 10; +#N canvas 258 163 640 725 10; +#X msg 131 535 print; +#X msg 132 568 new 5 8 8; +#X msg 127 139 init; +#X msg 128 314 train; +#X msg 129 336 test; +#X msg 128 427 write; +#X obj 70 599 ann_som 4 9 10; #X msg 70 49 1 0 0 1; #X msg 70 68 0 1 0 1; #X msg 70 87 2 1 0 0; -#X msg 128 118 init 0.5; -#X msg 128 138 init 1 0.5 0 0.5; -#X text 234 101 init all weights with "0"; -#X text 235 120 init all weights with "0.5"; -#X text 235 137 init weights for each sensor; -#X msg 128 163 learn 1; -#X msg 128 197 learn 1 0.9 0.1; -#X text 226 163 set learning rate to 1; -#X msg 128 180 learn 0.5 0.999; -#X text 227 179 set learning rate to 0.5 and factor to 0.999; -#X text 227 197 set learning rate to 1 \, factor to 0.9 and offset to 0.1; -#X msg 128 214 neighbour 1; -#X msg 128 231 neighbour 0.5 0.999; -#X msg 128 248 neighbour 1 0.9 0.1; -#X text 248 215 set neighbourhood to 1; -#X text 249 231 set neighbourhoodto 0.5 and factor to 0.999; -#X text 249 249 set neighbourhood to 1 \, factor to 0.9 and offset to 0.1; -#X text 180 269 set som to "train" mode (learn from sensor-input and output winning neuron); -#X text 179 291 set som to "test" mode (output winning neuron for sensor-input \, but do not learn !); -#X msg 129 328 rule INSTAR; -#X msg 129 345 rule OUTSTAR; -#X msg 129 362 rule KOHONEN; -#X text 218 327 learn with IN-STAR rule; -#X text 219 345 learn with OUT-STAR rule; -#X text 219 362 learn with KOHONENrule; -#X msg 128 405 write mysom.som; -#X msg 129 429 read; -#X msg 129 447 read mysom.som; +#X msg 128 158 init 0.5; +#X msg 128 178 init 1 0.5 0 0.5; +#X text 234 141 init all weights with "0"; +#X text 235 160 init all weights with "0.5"; +#X text 235 177 init weights for each sensor; +#X msg 128 203 learn 1; +#X msg 128 237 learn 1 0.9 0.1; +#X text 226 203 set learning rate to 1; +#X msg 128 220 learn 0.5 0.999; +#X text 227 219 set learning rate to 0.5 and factor to 0.999; +#X text 227 237 set learning rate to 1 \, factor to 0.9 and offset +to 0.1; +#X msg 128 254 neighbour 1; +#X msg 128 271 neighbour 0.5 0.999; +#X msg 128 288 neighbour 1 0.9 0.1; +#X text 248 255 set neighbourhood to 1; +#X text 249 271 set neighbourhoodto 0.5 and factor to 0.999; +#X text 249 289 set neighbourhood to 1 \, factor to 0.9 and offset +to 0.1; +#X text 180 309 set som to "train" mode (learn from sensor-input and +output winning neuron); +#X text 179 331 set som to "test" mode (output winning neuron for sensor-input +\, but do not learn !); +#X msg 129 368 rule INSTAR; +#X msg 129 385 rule OUTSTAR; +#X msg 129 402 rule KOHONEN; +#X text 218 367 learn with IN-STAR rule; +#X text 219 385 learn with OUT-STAR rule; +#X text 219 402 learn with KOHONENrule; +#X msg 128 445 write mysom.som; +#X msg 129 469 read; +#X msg 129 487 read mysom.som; #X text 156 68 present various data to the SOM; -#X text 203 495 for debugging; -#X text 207 530 create a new SOM with 8x8 neurons \, each having 5 sensors; -#X text 204 561 create a new SOM with 9x10 neurons \, each having 4 sensors; -#X floatatom 70 614 4 0 0; -#X text 113 618 winning neuron; +#X text 203 535 for debugging; +#X text 207 570 create a new SOM with 8x8 neurons \, each having 5 +sensors; +#X text 204 601 create a new SOM with 9x10 neurons \, each having 4 +sensors; +#X floatatom 70 654 4 0 0 0 - - -; +#X text 113 658 winning neuron; #N canvas 13 0 889 630 SOMs 0; #X text 76 27 SOM :: Self-Organized Maps; -#X text 55 53 SOMs are "Artificial Neural Networks" \, that are trying to learn something about the data presented to them without a supervisor/teacher.; +#X text 55 53 SOMs are "Artificial Neural Networks" \, that are trying +to learn something about the data presented to them without a supervisor/teacher. +; #X text 59 118 in short:; -#X text 120 119 the neuron \, whose weight-configuration matches the presented data best is the winner (its number (counting from the lower-left corner) is sent to the output); -#X text 121 163 to match the data better the next time it is presented \, the weights of the winning neuron are adjusted.; -#X text 121 188 the weights of the neurons neighbouring the winner are adjusted to match the data too \, but not so strong as the winner's.; +#X text 120 119 the neuron \, whose weight-configuration matches the +presented data best is the winner (its number (counting from the lower-left +corner) is sent to the output); +#X text 121 163 to match the data better the next time it is presented +\, the weights of the winning neuron are adjusted.; +#X text 121 188 the weights of the neurons neighbouring the winner +are adjusted to match the data too \, but not so strong as the winner's. +; #X text 121 276 lr(n+1)=lr(n)*factor; #X text 275 277 learning_rate=lr+offset; #X text 121 289 nb(n+1)=nb(n)*factor; #X text 275 290 neighbourhood=nb+offset; -#X text 121 230 both neighbourhood and learning-rate (==amount of how much the weights of the winner (and \, proportional \, the weights of the neighbours) are adjusted) are decreasing recursively with time.; -#X text 119 319 thus you will sooner or (most of the time) later get a "brain map" \, where similar inputs will activate neurons in specifique regions (like there are regions for seeing and regions for hearing in our brains); -#X text 97 381 there are various rules \, how to re-adjust the weights of the neurons : in-star \, out-star and kohonen (maybe there are others \, but these i found in literature); +#X text 121 230 both neighbourhood and learning-rate (==amount of how +much the weights of the winner (and \, proportional \, the weights +of the neighbours) are adjusted) are decreasing recursively with time. +; +#X text 119 319 thus you will sooner or (most of the time) later get +a "brain map" \, where similar inputs will activate neurons in specifique +regions (like there are regions for seeing and regions for hearing +in our brains); +#X text 97 381 there are various rules \, how to re-adjust the weights +of the neurons : in-star \, out-star and kohonen (maybe there are others +\, but these i found in literature); #X obj 607 220 +; #X text 640 182 ...; #X obj 579 185 * \$1; @@ -71,10 +92,15 @@ #X text 566 307 the neuron with the highest weighted sum; #X text 567 318 matches best and is therefore the winner; #X text 53 452 notes:; -#X text 101 453 each neuron of the SOM has n sensors. you have to present a list of n floats to the SOM to make it work; -#X text 102 482 you should init the weights for each sensor with the expected mean of the sensor values before you start training to get best and fastest results; -#X text 55 87 they were first proposed by the Finnish scientist T.Kohonen in the 80ies (i think).; -#X text 98 543 if you have no clue \, what's this all about \, maybe you do not need SOMs (which i doubt) or you should have a look at; +#X text 101 453 each neuron of the SOM has n sensors. you have to present +a list of n floats to the SOM to make it work; +#X text 102 482 you should init the weights for each sensor with the +expected mean of the sensor values before you start training to get +best and fastest results; +#X text 55 87 they were first proposed by the Finnish scientist T.Kohonen +in the 80ies (i think).; +#X text 98 543 if you have no clue \, what's this all about \, maybe +you do not need SOMs (which i doubt) or you should have a look at; #X text 118 577 http://www.eas.asu.edu/~eee511; #X text 118 591 http://www.cis.hut.fi/projects/ica; #X connect 13 0 22 0; @@ -87,8 +113,11 @@ #X connect 21 0 18 0; #X restore 535 44 pd SOMs; #X text 81 13 ann_som :: train and test Self-Organized Maps; -#X obj 73 660 ann_som test.som; -#X text 211 664 load a SOM-file; +#X obj 73 700 ann_som test.som; +#X text 211 704 load a SOM-file; +#X msg 128 119 rinit 10; +#X text 234 121 init all weights with time-seeded random values from +0 to 10; #X connect 0 0 6 0; #X connect 1 0 6 0; #X connect 2 0 6 0; @@ -112,3 +141,4 @@ #X connect 35 0 6 0; #X connect 36 0 6 0; #X connect 37 0 6 0; +#X connect 48 0 6 0; -- cgit v1.2.1