Apps optimized for the Qualcomm Hexagon DSP can run faster and consume less power. Today Qualcomm Technologies is introducing support for TensorFlow, the machine learning framework from Google. TensorFlow is now optimized for the Hexagon 682 DSP,
Pythonã§ãç¹ç°ã¡ã½ããããä½ãæ¹æ³ããç´¹ä»ãã¾ãã ç¹ç°ã¡ã½ããã¨ããã®ã¯ï¼ç§ãç¥ããããï¼Rubyçºç¥¥ã®ãã¨ã°ã§ããç¹å®ã®ãªãã¸ã§ã¯ãã ããæã¤ã¡ã½ãããã®ãã¨ãã¤ã³ã¹ã¿ã³ã¹ã¡ã½ããã¯ç¹å®ã®ã¯ã©ã¹ã®ã¤ã³ã¹ã¿ã³ã¹ã§ããã°ã©ã®ã¤ã³ã¹ã¿ã³ã¹ãããå¼ã³åºããã¨ãã§ãã¾ãããç¹ç°ã¡ã½ããã¯ããç¹å®ã®ã¤ã³ã¹ã¿ã³ã¹ããããå¼ã³åºããã¨ãã§ãã¾ããã types ã©ã¤ãã©ãªã® MethodType ã¨ããã³ã³ã¹ãã©ã¯ã¿ã使ãã°Pythonã§ãç¹ç°ã¡ã½ãããä½ããã¨ãã§ãã¾ãã å ·ä½çã«è¦ã¦ããã¾ãã # ã©ã¤ãã©ãªã®èªã¿è¾¼ã¿ from types import MethodType class Dog(object): def __init__(self, name): self.name = name d1 = Dog(âinuâ) # 以ä¸ã§ç¹ç°ã¡ã½ããã追å ãã¦ããã¾ã # ã¾ãã¯ç¹ç°ã¡ã½ã
Pythonã§ãæ¢åã®ã¯ã©ã¹ã«ã¤ã³ã¹ã¿ã³ã¹ã¡ã½ããã追å ããæ¹æ³ããç´¹ä»ãã¾ãã æ¢åã®ã¯ã©ã¹ã«ã¡ã½ããã追å ããã«ã¯æ¬¡ã®æé ãè¸ã¿ã¾ãã ã¾ãé¢æ°ãå¥éå®ç¾©ãã¦ãã ãã®é¢æ°åãã¯ã©ã¹ã®ã¢ããªãã¥ã¼ãã«ãã å ·ä½ä¾ãè¦ã¦ã¿ã¾ãã # __init__ ã¡ã½ããã ããåãã Dog ã¯ã©ã¹ class Dog(object): def __init__(self, name): self.name = name # 以ä¸ã§ Dog ã¯ã©ã¹ã« count_number ã¨ããã¤ã³ã¹ã¿ã³ã¹ã¡ã½ããã追å ãã # 01 ã¾ãã¯é¢æ°ãå®ç¾© def count_number(self): print "%s counts: one! one!" % self.name # 02 å®ç¾©ããé¢æ°ãã¯ã©ã¹ã®ã¢ããªãã¥ã¼ãã«è¿½å Dog.count_number = count_number # çµæ ta
ãªãï¼ @staticmethod ã®ãã³ã¬ã¼ã¿ãç¨ãã¦ï¼éçã¡ã½ããã¨ãã¦å®ç¾©ãã¦ããã¾ãï¼ sigmoid() ã¯æ°å¦é¢æ°ã§ããï¼å¤ã¯ãã®å¼æ°ã ãã«ä¾åãï¼ãªãã¸ã§ã¯ããã¯ã©ã¹ã®å 容ãç¶æ ã«ã¯ä¾åããªãã®ã§ï¼ãã®ããã«éçã¡ã½ããã¨ãã¦å®ç¾©ãã¾ããï¼ ããã§ã¯ï¼å®è¡ãã¦ã¿ã¾ãããï¼ sigmoid() ã¯éçã¡ã½ãããªã®ã§ï¼ãªãã¸ã§ã¯ããçæããªãã¦ãå®è¡ã§ãã¾ãï¼ In [10]: from lr1 import LogisticRegression In [11]: LogisticRegression.sigmoid(0.0) Out[11]: 0.5 In [12]: LogisticRegression.sigmoid(1.0) Out[12]: 0.7310585786300049 In [13]: 1.0 / (1.0 + 1.0 / np.e) Out[13]: 0.7
ç±³Yahoo!ã¯ã主è¦äºæ¥ãç±³Verizonã«å£²å´å¾ãä¼æ¥åããAltabaãã«å¤æ´ãããå社ã米証å¸åå¼å§å¡ä¼ï¼SECï¼ã«æåºãã1æ9æ¥ä»ã®ææ¸ã§æããã«ãªã£ãã 両社ã¯2016å¹´7æãVerizonãYahoo!ã®æ¤ç´¢ãåºåããã¥ã¼ã¹ããã¡ã¤ãã³ã¹ãã¹ãã¼ããç´2å2500ä¸äººã®MAUãæããã¡ã¼ã«ãµã¼ãã¹ãªã©ãã»ã¨ãã©ã®äºæ¥ãè²·åãããã¨ã§åæããã¨çºè¡¨ãããå½æçºè¡¨ãããè²·åç·é¡ã¯ç´48åãã«ãVerizonã¯Yahoo!ã®ãã©ã³ããæ®ãè¦è¾¼ã¿ã ã Yahoo!ã¯ãã¤ãã¼æ¥æ¬æ³äººæ ªã®ç´35ï¼ ã¨ãä¸å½Alibabaæ ªã®ç´15ï¼ ã¯ä¿æããAltabaã¨ããæè³ä¼æ¥ã«ãªãã ããã«ä¼´ããããªããµã»ã¡ã¤ã¤ã¼CEOãå«ã5人ãYahoo!ã®åç· å½¹ãéãã ã¡ã¤ã¤ã¼æ°ã«ã¤ãã¦ã¯ãVerizonåä¸ã®AOLã®ãã£ã ã»ã¢ã¼ã ã¹ããã³ã°CEOãè²·åçºè¡¨æ®µéã§ããè²·åå¾ã®ãã¸ã·ã§ã³ã¯æªå®ãã¨ãã¦ãã
ãªã³ã¯ www.facebook.com æ¨æ¸¡ åç¥ - ä»æ¥ãã¾ãã¨ããµã¤ãã£ã³ã°ãªä¸æ¥ã«ãæ¦éé«æ ¡ã®å¤§å 輩ã§ããå¤å·å¤§å çãäºåæ³ã®èµ·æ¥å®¶ãç§ã®äºåæã«é£ã... | Facebook ä»æ¥ãã¾ãã¨ããµã¤ãã£ã³ã°ãªä¸æ¥ã«ãæ¦éé«æ ¡ã®å¤§å 輩ã§ããå¤å·å¤§å çãäºåæ³ã®èµ·æ¥å®¶ãç§ã®äºåæã«é£ãã¦ãã¦ããã¾ããã ææ°ã®æ¥çµãã¬ã³ãã£ã¼ã« æ£®å· äº® (Akira Morikawa) ãããç´¹ä»ãã¦ãã 仲山 ä»ä¹å© (Nakayama Jinnosuke)... AtsukoOrikasa @Rutice_jp âã¾ãã¯ã»ãã¥ãªãã£ã¼ã®åéã§ãâä½ãã®åè«ã ãããï¼ / âæ¨æ¸¡ åç¥ - ä»æ¥ãã¾ãã¨ããµã¤ãã£ã³ã°ãªä¸æ¥ã«ãæ¦éé«æ ¡ã®å¤§å 輩ã§ããå¤å·å¤§å çãäºåæ³ã®èµ·æ¥å®¶ãç§ã®äºåæã«é£ã... | Facebookâ (1 user) htn.to/jib2Wq 2016-11-07 16:
Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.
å²ç¢AI âAlphaGoâ ã¯ãªãå¼·ãã®ã? ï½ãã£ã¼ãã©ã¼ãã³ã°ãã¢ã³ãã«ã«ãæ¨æ¢ç´¢ãå¼·åå¦ç¿ï½ 2016/04/15 大槻 ç¥å² 2016/04/15 2 ⢠èæ¯ â¢ å²ç¢AIã«ããããã£ã¼ãã©ã¼ãã³ã° ⢠å²ç¢AIã«ãããæ¢ç´¢ ⢠å²ç¢AIã«ãããå¼·åå¦ç¿(ãªã©) ⢠ã¾ã¨ã ç®æ¬¡ 2016/04/15 3 ⢠AlphaGo以å â æ¥æ¬ã®å²ç¢ãã©ã°ã©ã Zençã¯ããæ£å£«ã«4åå±ã§åå©(ã¢ããã¥ã¢é«æ®µè ã¬ãã«) â 人éãã£ã³ããªã³ã¬ãã«ã«ãªãã®ã¯10å¹´å¾ä½ã¨æããã¦ãã ⢠2015/10 â AlphaGoãã¨ã¼ããããã£ã³ããªã³ã®Fan Hui äºæ®µã«5å0æ*1 ⢠2016/01 â Google Deep Mind ãNature èªã«ãAlphaGoã«é¢ããè«æ*1 ãçºè¡¨ ⢠å¸è²©ã½ãã(Zen, Crazy Stone â¦)ã«å¯¾ã494å1æ ⢠2016/0
天çéä¸ãå¨ä½ï¼ï¼å¹´ãç¯ç®ã¨ãã¦è²ä½ãå¸æããã¦ãããã¨ãåããæ¿åºã¯ãå¹³æï¼ï¼ï¼ï¼ï¼ï¼ï¼ï¼å¹´ï¼æï¼æ¥ï¼å æ¥ï¼ã«ç太åãã¾ã®å¤©çå³ä½ã«ä¼´ãåå¼ãè¡ããåæ¥ããæ°å å·ã¨ããæ¹åã§æ¤è¨ã«å ¥ã£ããå½æ°çæ´»ã¸ã®å½±é¿ãæå°éã¨ããã«ã¯å æ¥ã®è²ä½ãæã¾ããã¨å¤æãããè²ä½ã«ä¼´ãé¢é£æ³æ¡ã¯ãæèè ä¼è°ã®å ±åã¨è¡å両é¢ã®è«è°ãè¸ã¾ããï¼æä¸æ¬ã«ãå½ä¼ã«æåºããè¦éããè²ä½ã¯ãä¸ä»£éããã¨ãã¦çå®¤å ¸ç¯æ¹æ£ã¯æå°éã«ã¨ã©ããæ¹åã§æ¤è¨ãé²ããã è¤æ°ã®æ¿åºé¢ä¿è ãæããã«ãããè²ä½ã®æ¥æã«é¢ãã¦ã¯ãâ年以å ã«æ¿ä»¤ã§å®ãããã¨ãã¦æ³æ¡ã«æè¨ãããç室ä¼è°ãçµã¦é£è°æ±ºå®ããæ¹éã å ·ä½çã«ã¯ãå¹³æï¼ï¼å¹´å æ¥ãå½äºè¡çºã§ãããå£ç½çæ¿ç¶ã®åãï¼ä¸ç¨®ã®ç¥å¨çå¼ãç¶ãï¼ã¨ãå³ä½å¾æè¦ã®åãï¼ä¸æ¨©ã®é·ãã®åæè¬ï¼ãå®®ä¸ã§è¡ããå®æ¿é·å®ãéããã«æ°å å·ãçºè¡¨ããæ¹åã§æ¤è¨ãã¦ããã çä½ç¶æ¿ã«ä¼´ãéè¦å礼ã§ãã大åç¥ã¯ãæº
ãå²ç¢AIï¼äººå·¥ç¥è½ï¼ã¯ããæ£å£«ã®è½åãé¥ãã«è¶ ãã¦ãã¾ã£ããããã«é²åãé²ã¿è¿½ãã¤ããã¨ã¯ã§ããªãã ããããå²ç¢AIã«ããããããæ£å£«ã®å¤§æ©ææå 段ã¯J-CASTãã¥ã¼ã¹ã®ã¤ã³ã¿ãã¥ã¼ã«ããèªã£ãã ãMasterãã¨åä¹ãã¢ã«ã¦ã³ããã¤ã³ã¿ã¼ãããå²ç¢ãµã¤ããæ±æ´å²ç¢ãã§ç¢ºèªãããã®ã¯2016å¹´12æ29æ¥ããã¾ãã®å¼·ããã大人æ°ãã³ã¬ããã«ã«ã®ç¢ãã®ç»å ´äººç©ã»ãµã¤(è¤åä½çº)ã§ã¯ãªãã®ãããªã©ã¨åãæ²æ±°ãããããã°ã¼ã°ã«ã¯æ¥æ¬æéã®17å¹´1æ5æ¥ãèªç¤¾ãéçºããå²ç¢AIã ã¨å ¬è¡¨ãããæ¢ã«ä¸çã®ãããããç¸æã«60é£åãã¦ãã¦ãããªãæ£å£«ã¯ããããªãã®ã ã¨ããã 16å¹´æ«ã«ãããã«å¿½ç¶ã¨ç¾ãã ãã§ã¹ãå°æ£ãªã©ããããããæç ´ããAIãç»å ´ãã¦ããå²ç¢ã ãã¯æã¡æãè¤éãªãã人éãè¶ ããããªãã ãããã¨ããã®ãé·ãéã®å®èª¬ã ã£ãããããè¦ããã®ã16å¹´3æä¸æ¬ã«è¡ãããã°ã¼ã°ã«åä¸ã®ä¼
Recent Advances in Convolutional Neural Networks Jiuxiang Gua,â , Zhenhua Wangb,â , Jason Kuenb , Lianyang Mab , Amir Shahroudyb , Bing Shuaib , Ting Liub , Xingxing Wangb , Gang Wangb aInterdisciplinary Graduate School, Nanyang Technological University, Singapore bSchool of Electrical and Electronic Engineering, Nanyang Technological University, Singapore Abstract In the last few years, deep lear
å æ¥ï¼èº«å ã®åå¼·ä¼(&ã©ãã®åå¼·ä¼)ã§ï¼Deep Learningã«ã¤ãã¦ã話ãã¦ãã¾ããï¼ããã¾ã§èå³ããªãããã ã£ãã®ã«ä½æ æ¥ã«ï¼ã¨ããã®ã¯ããã¦ããã¦ï¼ ç´¹ä»ããã®ã¯ï¼Deep Learningã®ç¬¬ä¸äººè ã®ã²ã¨ãï¼ Yoshua Bengioå çèªèº«ãå·çãããï¼ä»¥ä¸ã®è«æï¼ Yoshua Bengio, Practical recommendations for gradient-based training of deep architectures, arXiv:1206.5533v2, 2012 ã©ãããæ¸ç±ã®è稿ã®ããã§ï¼Bengioå çã®é·å¹´ã®ç 究ã§å¾ããããã¾ãã¾ãªãã¦ãã¦(æè¿ã®ææ³ã¾ã§)ããã£ããè©°ãè¾¼ã¾ãã¦ãã¾ãï¼ãããï¼ ä»¥åããæ°ã«ã¯ãªãã¤ã¤ãï¼ã¡ãã£ã¨åéãå¤ã(30ãã¼ã¸ããããã)ã®ã§ï¼ãªããªãæãåºããã¨ãã§ããªãã£ãã®ã§ããï¼ããããã¤ã«æ°ãåºã¦ãã
æ¾å´ä¸èãã¯ã©ãã·ã£ã¼ä¸å¸ï¼å¹³æ°ã§é¨ä¸ã追ãè©°ãã人ãã¡ãï¼PHPæ°æ¸)ããéãããã ãã¾ããããããã¨ããããã¾ãã èªåã®åºä¸ã®ããã«ã次ã ã«é¨ä¸ãã¤ã¶ãã¦ãã人ã®ç²¾ç¥æ§é ã¨å¯¾å¦æ³ããæ°å¤ãã®å®ä¾ã«æ¥ããç²¾ç¥ç§ã®ç£æ¥å»ããããã解説ã ã¯ã©ãã·ã£ã¼ã»ã¸ã§ã¦ãããªãã£ã¦ãã¯ã©ãã·ã£ã¼ä¸å¸ã§ãã èè ã®æ¾å´ããã¯æ°å°ãªãç£æ¥ç²¾ç¥å»å¦ã®å°é家ããããããã¯ãã©ã大ããªåé¡ã¨ãªããé»é第äºäºä»¶ãä¸æ ãè³ããã¦ããä»æ¥ãæ¯éå¤ãã®äººã ã«èªã¾ããã¹ãæ¬ã§ãã ã¨ã¨ãã«ãããã«æããã¦ããããã¤ãã®å®ä¾ãèªãé²ãã«ã¤ããå§åçã«å¤ãã®çµç¹äººãã¡ã¯ãããã£ããããæã社ã«ããããããã¨ããæããä½åãããã§ããããããããå¤ãã®ä¼ç¤¾ãçµç¹ã®ã¡ã³ã¿ã«ãã«ã¹ãè¦ã¦ãããã®ã®çµé¨å¤ã¨ãã¦ãä¸é¨ä¸å ´ä¼æ¥ã®å½¹å¡ã®ãã¡æ°äººã¯ãã¯ã©ãã·ã£ã¼ä¸å¸ãããããã¨ãããã¨ã¯ã§ããã ãããã¨èè ã¯è¿°ã¹ã¦ãã¾ãã å½¼ãã¯ã©ãã·
ãç¥ãã
é害
ã©ã³ãã³ã°
ãªãªã¼ã¹ãé害æ å ±ãªã©ã®ãµã¼ãã¹ã®ãç¥ãã
ææ°ã®äººæ°ã¨ã³ããªã¼ã®é ä¿¡
j次ã®ããã¯ãã¼ã¯
kåã®ããã¯ãã¼ã¯
lãã¨ã§èªã
eã³ã¡ã³ãä¸è¦§ãéã
oãã¼ã¸ãéã
{{#tags}}- {{label}}
{{/tags}}