際際滷shows by User: YukiHayashi3 / http://www.slideshare.net/images/logo.gif 際際滷shows by User: YukiHayashi3 / Sat, 19 Sep 2015 12:24:40 GMT 際際滷Share feed for 際際滷shows by User: YukiHayashi3 GTC Japan 2015 - Experiments to apply Deep Learning to Forex time series data /slideshow/gtc-japan-2015-experiments-to-apply-deep-learning-to-forex-time-series-data/52963260 alpaca-gtcjp-2015-150919122440-lva1-app6891
Since most of previous studies about pattern recognition on FX time series data were done by handcrafted features which were not easy to program and lacking flexibility. We propose the LSTM based deep neural network and its training method which helps traders to duplicate their strategies by just feeding what they see on the chart as training samples for AI.]]>
Since most of previous studies about pattern recognition on FX time series data were done by handcrafted features which were not easy to program and lacking flexibility. We propose the LSTM based deep neural network and its training method which helps traders to duplicate their strategies by just feeding what they see on the chart as training samples for AI.]]> Sat, 19 Sep 2015 12:24:40 GMT /slideshow/gtc-japan-2015-experiments-to-apply-deep-learning-to-forex-time-series-data/52963260 YukiHayashi3@slideshare.net(YukiHayashi3) GTC Japan 2015 - Experiments to apply Deep Learning to Forex time series data YukiHayashi3 Since most of previous studies about pattern recognition on FX time series data were done by handcrafted features which were not easy to program and lacking flexibility. We propose the LSTM based deep neural network and its training method which helps traders to duplicate their strategies by just feeding what they see on the chart as training samples for AI. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/alpaca-gtcjp-2015-150919122440-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Since most of previous studies about pattern recognition on FX time series data were done by handcrafted features which were not easy to program and lacking flexibility. We propose the LSTM based deep neural network and its training method which helps traders to duplicate their strategies by just feeding what they see on the chart as training samples for AI.
GTC Japan 2015 - Experiments to apply Deep Learning to Forex time series data from Yuki Hayashi
]]> 76403 34 https://cdn.slidesharecdn.com/ss_thumbnails/alpaca-gtcjp-2015-150919122440-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-YukiHayashi3-48x48.jpg?cb=1596422302 I'm an embedded & realtime distributed system development engineer specialized in computer graphics & computer vision field. My focus in science is machine learning technologies, and focus in engineering is optimization in both algorithmic & hardware level as well as highly distributed p2p mesh networking. I started working on computer vision technologies since 2001 at the university, and resulted as several patents. I was also working on realtime 2D/3D computer graphics technologies since long time before GPU(hardware vector processor & rasterizer) came out which brought me deep understanding about mathematics and performance optimization technics behind computer gra... alpaca.ai