很好 我采用得是串行方式对bp网络进行训练，为何训练时误差dsum约来越大？？望指教！-good, I have used in serial mode is the right bp network training, training errors are about to dsum greater? ? Look weekend!
SHOW FULL COLUMNS FROM `jrk_downrecords` [ RunTime:0.001380s ]
SELECT `a`.`aid`,`a`.`title`,`a`.`create_time`,`m`.`username` FROM `jrk_downrecords` `a` INNER JOIN `jrk_member` `m` ON `a`.`uid`=`m`.`id` WHERE `a`.`status` = 1 GROUP BY `a`.`aid` ORDER BY `a`.`create_time` DESC LIMIT 10 [ RunTime:0.092989s ]
SHOW FULL COLUMNS FROM `jrk_tagrecords` [ RunTime:0.001278s ]
SELECT * FROM `jrk_tagrecords` WHERE `status` = 1 ORDER BY `num` DESC LIMIT 20 [ RunTime:0.002037s ]
SHOW FULL COLUMNS FROM `jrk_member` [ RunTime:0.001237s ]
SELECT `id`,`username`,`userhead`,`usertime` FROM `jrk_member` WHERE `status` = 1 ORDER BY `usertime` DESC LIMIT 10 [ RunTime:0.003633s ]
SHOW FULL COLUMNS FROM `jrk_searchrecords` [ RunTime:0.001068s ]
SELECT * FROM `jrk_searchrecords` WHERE `status` = 1 ORDER BY `num` DESC LIMIT 5 [ RunTime:0.003850s ]
SELECT aid,title,count(aid) as c FROM `jrk_downrecords` GROUP BY `aid` ORDER BY `c` DESC LIMIT 10 [ RunTime:0.016330s ]
SHOW FULL COLUMNS FROM `jrk_articles` [ RunTime:0.001447s ]
UPDATE `jrk_articles` SET `hits` = 1 WHERE `id` = 22473 [ RunTime:0.001412s ]
