{"id":2628,"date":"2018-01-09T07:47:21","date_gmt":"2018-01-09T12:47:21","guid":{"rendered":"https:\/\/blogs.mathworks.com\/loren\/?p=2628"},"modified":"2018-01-16T10:28:06","modified_gmt":"2018-01-16T15:28:06","slug":"deep-learning-matlab-and-science","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/loren\/2018\/01\/09\/deep-learning-matlab-and-science\/","title":{"rendered":"Deep Learning, MATLAB, and Science"},"content":{"rendered":"<div class=\"content\"><!--introduction--><p>I recently attended the annual <a href=\"https:\/\/sites.agu.org\/\">AGU (American Geophysical Union)<\/a> meeting and, used the time at our booth to talk to many geoscientists about many different topics.  One that emerged as a big interest stemming from unfamiliarity is <a href=\"https:\/\/www.mathworks.com\/discovery\/deep-learning.html\">deep learning<\/a>.<\/p><!--\/introduction--><h3>Contents<\/h3><div><ul><li><a href=\"#1ca9c797-7b79-40c0-ad7b-f7e942731937\">Resources<\/a><\/li><li><a href=\"#52192d1f-47f2-4184-81b5-05c8f3bdf169\">Applications<\/a><\/li><li><a href=\"#e35e2139-4e2d-4480-9afb-1dab291adbaf\">Your Thoughts?<\/a><\/li><\/ul><\/div><h4>Resources<a name=\"1ca9c797-7b79-40c0-ad7b-f7e942731937\"><\/a><\/h4><p>At MathWorks we have been adding to our machine learning and deep learning repertoire ardently.  One reflection of this is <a href=\"https:\/\/blogs.mathworks.com\/deep-learning\/\">the newest blog<\/a>, on deep learning, authored by <a href=\"https:\/\/www.mathworks.com\/matlabcentral\/profile\/authors\/476476-steve-eddins\">Steve Eddins<\/a>, also the author of the <a href=\"https:\/\/blogs.mathworks.com\/steve\/\">Steve on Image Processing<\/a> blog.<\/p><h4>Applications<a name=\"52192d1f-47f2-4184-81b5-05c8f3bdf169\"><\/a><\/h4><p>Most applications of deep learning these days are focused on images, with signals coming along strongly now as well. Here's <a href=\"https:\/\/www.mathworks.com\/solutions\/deep-learning\/examples.html\">a link<\/a> to some MATLAB examples\/applications in more traditional areas like object detection.<\/p><p><img decoding=\"async\" vspace=\"5\" hspace=\"5\" src=\"https:\/\/blogs.mathworks.com\/images\/loren\/2018\/semanticSegmentation.jpg\" alt=\"\"> <\/p><p>In the sciences, successes have been reported in biological and medical studies.<\/p><p>In domains, such as geosciences, often data can be viewed as an image even if they don't represent an actual picture.  We had several discussions at AGU about possible applications of deep learning for seismic problems, atmospheric ones, and oceanographic ones.  And deep learning is certainly having some success in some remote sensing applications, from a quick web search.<\/p><h4>Your Thoughts?<a name=\"e35e2139-4e2d-4480-9afb-1dab291adbaf\"><\/a><\/h4><p>Do you know of any people or applications currently using deep learning in their work?  What domain?  What do you see looking forward to the application of deep learning in domains you know most about?  Let us know <a href=\"https:\/\/blogs.mathworks.com\/loren\/?p=2628#respond\">here<\/a>.<\/p><script language=\"JavaScript\"> <!-- \r\n    function grabCode_d88344dc2c6a449bae1e426f83470378() {\r\n        \/\/ Remember the title so we can use it in the new page\r\n        title = document.title;\r\n\r\n        \/\/ Break up these strings so that their presence\r\n        \/\/ in the Javascript doesn't mess up the search for\r\n        \/\/ the MATLAB code.\r\n        t1='d88344dc2c6a449bae1e426f83470378 ' + '##### ' + 'SOURCE BEGIN' + ' #####';\r\n        t2='##### ' + 'SOURCE END' + ' #####' + ' d88344dc2c6a449bae1e426f83470378';\r\n    \r\n        b=document.getElementsByTagName('body')[0];\r\n        i1=b.innerHTML.indexOf(t1)+t1.length;\r\n        i2=b.innerHTML.indexOf(t2);\r\n \r\n        code_string = b.innerHTML.substring(i1, i2);\r\n        code_string = code_string.replace(\/REPLACE_WITH_DASH_DASH\/g,'--');\r\n\r\n        \/\/ Use \/x3C\/g instead of the less-than character to avoid errors \r\n        \/\/ in the XML parser.\r\n        \/\/ Use '\\x26#60;' instead of '<' so that the XML parser\r\n        \/\/ doesn't go ahead and substitute the less-than character. \r\n        code_string = code_string.replace(\/\\x3C\/g, '\\x26#60;');\r\n\r\n        copyright = 'Copyright 2018 The MathWorks, Inc.';\r\n\r\n        w = window.open();\r\n        d = w.document;\r\n        d.write('<pre>\\n');\r\n        d.write(code_string);\r\n\r\n        \/\/ Add copyright line at the bottom if specified.\r\n        if (copyright.length > 0) {\r\n            d.writeln('');\r\n            d.writeln('%%');\r\n            if (copyright.length > 0) {\r\n                d.writeln('% _' + copyright + '_');\r\n            }\r\n        }\r\n\r\n        d.write('<\/pre>\\n');\r\n\r\n        d.title = title + ' (MATLAB code)';\r\n        d.close();\r\n    }   \r\n     --> <\/script><p style=\"text-align: right; font-size: xx-small; font-weight:lighter;   font-style: italic; color: gray\"><br><a href=\"javascript:grabCode_d88344dc2c6a449bae1e426f83470378()\"><span style=\"font-size: x-small;        font-style: italic;\">Get \r\n      the MATLAB code <noscript>(requires JavaScript)<\/noscript><\/span><\/a><br><br>\r\n      Published with MATLAB&reg; R2017b<br><\/p><\/div><!--\r\nd88344dc2c6a449bae1e426f83470378 ##### SOURCE BEGIN #####\r\n%% Deep Learning, MATLAB, and Science\r\n% I recently attended the annual <https:\/\/sites.agu.org\/ AGU (American\r\n% Geophysical Union)> meeting and, used the time at our booth to talk to\r\n% many geoscientists about many different topics.  One that emerged as a\r\n% big interest stemming from unfamiliarity is\r\n% <https:\/\/www.mathworks.com\/discovery\/deep-learning.html deep learning>.\r\n\r\n%% Resources\r\n% At MathWorks we have been adding to our machine learning and deep\r\n% learning repertoire ardently.  One reflection of this is\r\n% <https:\/\/blogs.mathworks.com\/deep-learning\/ the newest blog>, on deep\r\n% learning, authored by\r\n% <https:\/\/www.mathworks.com\/matlabcentral\/profile\/authors\/476476-steve-eddins\r\n% Steve Eddins>, also the author of the <https:\/\/blogs.mathworks.com\/steve\/\r\n% Steve on Image Processing> blog.\r\n\r\n%% Applications\r\n% Most applications of deep learning these days are focused on images, with\r\n% signals coming along strongly now as well. Here's\r\n% <https:\/\/www.mathworks.com\/solutions\/deep-learning\/examples.html a link>\r\n% to some MATLAB examples\/applications in more traditional areas like\r\n% object detection.  \r\n%\r\n% <<semanticSegmentation.jpg>>\r\n%\r\n% In the sciences, successes have been reported in\r\n% biological and medical studies.\r\n%%\r\n% In domains, such as geosciences, often data can be viewed as an image\r\n% even if they don't represent an actual picture.  We had several\r\n% discussions at AGU about possible applications of deep learning for\r\n% seismic problems, atmospheric ones, and oceanographic ones.  And deep\r\n% learning is certainly having some success in some remote sensing\r\n% applications, from a quick web search.\r\n\r\n%% Your Thoughts?\r\n% Do you know of any people or applications currently using deep learning\r\n% in their work?  What domain?  What do you see looking forward to the\r\n% application of deep learning in domains you know most about?  Let us know\r\n% <https:\/\/blogs.mathworks.com\/loren\/?p=2628#respond here>.\r\n##### SOURCE END ##### d88344dc2c6a449bae1e426f83470378\r\n-->","protected":false},"excerpt":{"rendered":"<div class=\"overview-image\"><img decoding=\"async\"  class=\"img-responsive\" src=\"https:\/\/blogs.mathworks.com\/images\/loren\/2018\/semanticSegmentation.jpg\" onError=\"this.style.display ='none';\" \/><\/div><!--introduction--><p>I recently attended the annual <a href=\"https:\/\/sites.agu.org\/\">AGU (American Geophysical Union)<\/a> meeting and, used the time at our booth to talk to many geoscientists about many different topics.  One that emerged as a big interest stemming from unfamiliarity is <a href=\"https:\/\/www.mathworks.com\/discovery\/deep-learning.html\">deep learning<\/a>.... <a class=\"read-more\" href=\"https:\/\/blogs.mathworks.com\/loren\/2018\/01\/09\/deep-learning-matlab-and-science\/\">read more >><\/a><\/p>","protected":false},"author":39,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[63,66,43],"tags":[],"_links":{"self":[{"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/posts\/2628"}],"collection":[{"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/users\/39"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/comments?post=2628"}],"version-history":[{"count":3,"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/posts\/2628\/revisions"}],"predecessor-version":[{"id":2640,"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/posts\/2628\/revisions\/2640"}],"wp:attachment":[{"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/media?parent=2628"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/categories?post=2628"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.mathworks.com\/loren\/wp-json\/wp\/v2\/tags?post=2628"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}