ã³ã°ãã«ã«ã¯ã足ããªãç¥èãæãä¸ãã¦ç解ããå¦ç¿ãµã¤ãã§ãã
ã³ã°ãã«ã«ã¯ã足ããªãç¥èãæãä¸ãã¦ç解ããå¦ç¿ãµã¤ãã§ãã
ä¸çã«ã¯ã¤ã³ã¿ã¼ãããæ¥ç¶ãè¡ããªãå ´æãå¤ãæ®ããã¦ããããããªå ´æã«ãã¤ã³ã¿ã¼ãããç°å¢ãæä¾ãã¹ãSpaceXããStarlinkè¨ç»ãã§äººå·¥è¡æãæã¡ä¸ããããFacebookãã2Africaãã§æµ·åºã±ã¼ãã«ãè¨ç½®ãããã¨ããããã¦ãã¾ããGoogleã¯ãç±æ°çãã§ã¤ã³ã¿ã¼ãããç°å¢ãæä¾ãããProject Loonãã2015å¹´ããç¶ãã¦ãã¾ãããå¼·åå¦ç¿ãå©ç¨ããAIã®éçºã«ãããããã¸ã§ã¯ãã大ããåé²ããã¨çºè¡¨ããã¾ããã Autonomous navigation of stratospheric balloons using reinforcement learning | Nature https://www.nature.com/articles/s41586-020-2939-8 Drifting Efficiently Through the Stratos
PyTorch, ONNX, Caffe, OpenVINO (NCHW) ã®ã¢ãã«ãTensorflow / TensorflowLite (NHWC) ã¸ãæ軽ã«å¤æããDeepLearningCaffeTensorFlowPyTorchONNX æ¥æ¬èªãEnglish 1. ã¯ããã« ãã¤ãå·¦ä¸éãçããããªããããããªãµãããè¨äºã°ãããéç£ãã¦ãã¾ãã ãã®è¨äºã®æé ãå®æ½ããã¨ã æçµçã« PyTorch製 é«ç²¾åº¦Semantic Segmentation ã® U^2-Net ã TensorFlow Lite ã¸å¤æãããã¨ãã§ãã¾ãã ä¸å³ã®ãããªæãã§ãã TensorFlow ãã¡ããã¡ãæ±ãã«ããã§ãã æ¥ã å ¬éãããææ°ã®ã¨ã¦ãé¢ç½ãã¢ãã«ã¯è»ä¸¦ã¿PyTorchå®è£ ã§ããããªãã§TensorFlowã§å®è£ ãã¦ãããªããã ï¼ï¼ ã¨ã常æ¥é æã£ã¦ãã¾ãã è«æã®ãã³ãã
3ã¤ã®è¦ç¹ âï¸ Skip-Layer Excitationã¨self-supervised Discriminatorãææ¡ãããã©ã¡ã¼ã¿ã®å¤§å¹ åæ¸ã«æå âï¸ å°éãã¼ã¿ã§ãå¦ç¿å¯è½ âï¸ 1024Ã1024ã®ç»åãGPU1æãæ°æéã§å¦ç¿å¯è½ Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis written by Anonymous (Submitted on 29 Sep 2020) Comments: Accepted at ICLR2021 Subjects: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV) Comm æ¦è¦ ããã¾ã§ã®G
ã¯ããã« ç¾å¨DNN(Deep Neural Network)ã®å®è£ ã«ããã¦ãFPGAã®æ´»ç¨ã¯ãã°ãè°è«ã®å¯¾è±¡ã«ãªã£ã¦ãã¾ãããã¡ããDNNåéå ¨ä½ããããã¨ããããªé¨é¡ã«å ¥ãã¨ã¯èãã¾ãããFPGAãã³ãã¼ã¯ããã«é常ã«åãå ¥ãã¦ãããä½æãããããã¯ã¼ã¯ã®ãããã¤å ã¨ãã¦FPGAãé¸æãããããªããããªå種ã®ã½ãªã¥ã¼ã·ã§ã³ãç¨æããå§ãã¦ãããæ¥ã é²åãã¦ãã¾ãã ããã§ã®FPGAã®ã¡ãªããã¯ãä½æ¶è²»é»åã§ãã£ãããã³ã¹ãã§ãã£ãããã¾ããDNNã®å®è¡ã«ã¯ã¯ã©ã¦ãã§ãã£ã¦ãé»åã¨ããã©ã³ãã³ã°ã³ã¹ãã¯é¦¬é¹¿ã«ãªãã¾ããããã¨ãã¸ã³ã³ãã¥ã¼ãã£ã³ã°ãç¹ã«ããããªã¼é§åã®ã¢ãã¤ã«åéã«ããã¦ã¯é»åã¯æ¥µãã¦éè¦ã§ããã¾ãã¤ãã·ã£ã«ã³ã¹ãã®éè¦æ§ã¯ã©ã¡ããåãã§ãããã ããã§FPGAãã³ãã¼ã¯ããã£ã¦ããGPUã¨åãããã«éçºã§ãã¾ããããã£ãããã¬ã¼ãºã«ãGPUã使ã£ã¦ç 究éçºããã¦ããå¤ã
ã¯ããã« å¾æ¥ã®ãã¼ã»ãããã³ã¢ãã«ã使ã£ãå¦ç¿ã§ã¯ãªããåè·¯ãã®ãã®ãå¾®åãã¦FPGAãç´æ¥å¦ç¿ãã¦ãã¾ããã¨ããå½ãµã¤ããªãªã¸ãã«ã®ãã£ã¼ãã©ã¼ãã³ã°LUT-Networkã§ãããããã®ã¨ããæ·±ãããããå¦ç¿ãããããã«è¸ç(Knowledge Distillation)ã«åãçµãã§ãã¾ããã ãã®ä¸ã¤ã®ææã¨ãã¦ãMNISTãã¼ã¿ã使ã£ãã»ãã³ãã£ãã¯ã»ã°ã¡ã³ãã¼ã·ã§ã³(ãã©ã)ã試ãã¦ã¿ãã®ã§ããã°ã«è¨é²ãã¦ããã¾ãã ã¾ãã¯å ã«çµæ ã¾ãå ã«ææ°ã®çµæãè¨è¼ãããã¾ããMNISTãã¼ã¹ã®ç»åãå ¥åãã¦ãããããã®æ°åé åãè²å¡ãããã»ãã³ãã£ãã¯ã»ã°ã¡ã³ãã¼ã·ã§ã³(ãã©ã)ãå¦ç¿ããã¦ã¿ã¾ããã å ¥åç»å åºåç»å ä¸è¨ã®å ¥åç»åããã¨ã« Verilog ã®RTLã·ãã¥ã¬ã¼ã·ã§ã³ã§å¾ãçµæç»åã以ä¸ã§ãã FPGAãªã½ã¼ã¹ ä¸è¨ãå®éã«RTLãåæããå ´åã®ãªã½ã¼ã¹éã§ããDNN
Machine learning is complex. For newbies, starting to learn machine learning can be painful if they donât have the right resources to learn from. Most of the machine learning libraries are difficult to understand and the learning curve can be a bit frustrating. I am creating a repository on GitHub (cheatsheets-ai) containing cheatsheets for different machine learning frameworks, gathered from diff
æ¬ããã°ã©ã ã®æ大ã®ç¹å¾´ã®ä¸ã¤ã¯ãå ¨ã¦ã®ãããã¯ã«ã¤ãã¦ãæ¼ç¿ãä¸å¿ã«æ§æããã¦ããç¹ã§ããå®éã«æãåãããªããç解ãé²ãããã¨ã§ãå¹çããå¦ç¿ãããã¨ãã§ãã¾ãã å®éã«ã¢ãã«ãå¦ç¿ãããªããæè¡ãç¿å¾ããæ¬æ ¼çãªæ¼ç¿å 容ã¨ãªã£ã¦ãã¾ããDeep Learningã¯ãã¢ãã«ãå®éã«å¦ç¿ããæ§åã観測ãããã©ã¡ã¼ã¿ã調æ´ãããã¨ã§ã¢ããªã±ã¼ã·ã§ã³ã«å¿ããããã©ã¼ãã³ã¹æ大åãè¡ããã¨ãé常ã«éè¦ãªæè¡ã§ããããã®ä¸é£ã®æµããå ¨ã¦ã®æ¼ç¿ã§çµé¨ããªããéè¦ãªè¦ç´ ã身ã«ã¤ãããã¨ãå¯è½ã§ãã
TensorFlowã§ç»åèªèãããå¤å¥æ©ããä½ã TensorFlowã¨ã¯ Googleã®æ©æ¢°å¦ç¿ãªã¼ãã³ã½ã¼ã¹ã½ããã¦ã§ã¢ã©ã¤ãã©ãªã§ãã å ¬å¼ãã¼ã¸ ç®çã®åå®ç¾© TensorFlowã使ç¨ãã¦ãç»åèªèãããªãªã¸ãã«ç»åå¤å¥æ©ããä½ãã¾ãã å¿ è¦ãªãã® ã»Macbook Air macOS Sierra 10.12.6 ã¡ã¢ãªã大ããã»ã©æã¾ãã ã»ããã¹ãã¨ãã£ã¿ æ¨å¥¨ï¼Atom ä½æã®æµã å¿ è¦ãªãã®ãæºåãã ä»®æ³ç°å¢ã«å ¥ã TensorFlowãå ¥ãã æ師ãã¼ã¿ãç¨æãã å¦ç¿ããã¦ãã¢ãã«ãä½ã ã¢ãã«ã使ã£ã¦å¤å¥ããã Tensorflowã使ã£ã¦ç°¡åãªãããå¤å¥æ©ããä½ã£ã¦ã¿ã¾ãã ãªããç°å¢ã¨ãã¦Python3ç³»ãåæã¨ãã¦ãã¾ããPythonã®ãã¼ã¸ã§ã³ã¯ python --version ã§ç¢ºèªãã¦ãã ããã 1. Tensorflowã使ãç°å¢ãä½ã Ten
ããã«ã¡ã¯ãã¨ã¯ãµã¦ã£ã¶ã¼ãºAIã¨ã³ã¸ãã¢ã®é è¤ã§ãã ãã®åº¦exaBaseã®ãç©ä½åå¤å¥ãã¢ãã«ã®ç´¹ä»ãã¼ã¸ã«ããã®å ´ã§è©¦ãããã¢æ©è½ã追å ãã¾ããã ååã®ãåçã«åã£ã¦ããªãã¨ããã復å ãããã¨ã¨ãã«ãå®è£ ã«ããã£ã¦ã¯Tensorflow.jsã¨ãããã¬ã¼ã ã¯ã¼ã¯ã使ã£ã¦ãã¾ãã ãã®è¨äºã§ã¯ãTensorflow.jså°å ¥ã¾ã§ã®ç°¡åãªè§£èª¬ã¨æ³¨æç¹ãããã³æ°ãããã¢ã®æä½æ¹æ³ãç´¹ä»ãããã¨æãã¾ãã Tensorflow.jsã¨ã¯ å ¬å¼ãµã¤ã ç¹å¾´ éçºç°å¢ ã¢ãã«ã®æ¸ãåºã ã¢ãã«ã®èªã¿è¾¼ã¿ å®è¡ ã¢ãã«ãèªã¿è¾¼ããªãå ´å ç©ä½åå¤å¥ã㢠æä½æ¹æ³ çµæ ã¾ã¨ã Tensorflow.jsã¨ã¯ Tensorflowãããã¯Kerasã§æ¸ãããæ©æ¢°å¦ç¿ã¢ãã«ããJavaScriptã§æ±ããããã«ãããã¬ã¼ã ã¯ã¼ã¯ã§ãã å¦ç¿æ¸ã¿ã¢ãã«ã«ããæ¨è«ã主ãªå¿ç¨ã¨èãããã¾ãããã¢ãã«ã®æ§ç¯
æè¿ãã¿ã¤ãã³ã°ãåãããããã«ãæµ·å¤ã®ï¼äººã®èè ããåãææãåããã ãæ¥æ¬ã®ããããã»ï¼¡ï¼©ï¼äººå·¥ç¥è½ï¼ç 究éçºã¯ã¸ã§ã³ãã¼ãã¤ã¢ã¹ãå©é·ãã¦ããããªã社ä¼ã¯åé¡è¦ããªãã®ãï¼ã ï¼äººç®ã¯ãEUï¼æ¬§å·é£åï¼ã®ç§å¦æè¡ã¤ããã¼ã·ã§ã³ãæ å½ããå¹¹é¨ã§ãããï¼äººç®ã¯ã¹ã¦ã§ã¼ãã³ã®ç§å¦æè¡æ å½ã®æ°â¦
Accessibility View text version Categories Technology Upload Details Uploaded via SlideShare as Adobe PDF Usage Rights © All Rights Reserved Statistics Favorites 2 Downloads 0 Comments 0 Embed Views 0 Views on SlideShare 0 Total Views 0 Deep learning â Presentation Transcript Deep Learning æ ªå¼ä¼ç¤¾ã¦ãµã®ã£ äºæ¨ç° åä¹ 2012/11/0912å¹´11æ9æ¥éææ¥ èªå·±ç´¹ä» â¤ æ ªå¼ä¼ç¤¾ã¦ãµã®ã£ã®ã¨ã³ã¸ã㢠⤠æ©æ¢°å¦ç¿ãèªç¶è¨èªå¦çãçµåãæé©å ⤠iPhone, Android, Rails ⤠ãª
Musings on data science, machine learning and stats. I've been impressed in recent months by the number and quality of free datascience/machine learning books available online. I don't mean free as in some guy paid for a PDF version of an O'Reilly book and then posted it online for others to use/steal, but I mean genuine published books with a free online version sanctioned by the publisher. That
ãªãªã¼ã¹ãé害æ å ±ãªã©ã®ãµã¼ãã¹ã®ãç¥ãã
ææ°ã®äººæ°ã¨ã³ããªã¼ã®é ä¿¡
å¦çãå®è¡ä¸ã§ã
j次ã®ããã¯ãã¼ã¯
kåã®ããã¯ãã¼ã¯
lãã¨ã§èªã
eã³ã¡ã³ãä¸è¦§ãéã
oãã¼ã¸ãéã
{{#tags}}- {{label}}
{{/tags}}