{"id":20604,"date":"2018-06-22T08:30:47","date_gmt":"2018-06-22T15:30:47","guid":{"rendered":"https:\/\/insidebigdata.com\/?p=20604"},"modified":"2018-06-23T11:05:50","modified_gmt":"2018-06-23T18:05:50","slug":"advancements-dynamic-efficient-deep-learning-systems","status":"publish","type":"post","link":"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/","title":{"rendered":"Advancements in Dynamic and Efficient Deep Learning Systems"},"content":{"rendered":"

\"\"Deep Learning Research<\/strong><\/span><\/p>\n

We’re seeing much hype in the marketplace about the potential of AI, especially with respect to computer vision systems and its ability accelerate the development of everything from self-driving cars to autonomous robots. While such systems have proven their ability to accurately identify images and multimedia with minimal human intervention, in reality, the deep learning-based methods used today take too long to train, consume far too much power, and may harvest vast amounts of data unnecessarily.<\/p>\n

To create more dynamic and efficient deep learning systems, that don\u2019t compromise accuracy, IBM Research<\/a> is exploring new and novel computer vision techniques from both a hardware and software angle.<\/p>\n

On the hardware side<\/strong><\/p>\n

Good results come from a brain-inspired system that uses the IBM TrueNorth neuromorphic chips together with a pair of vision sensors that act like eyes. Together the system can respond to changes in the environment to provide imagery in stereo with a sense of depth. Simply put, they\u2019re able to hone in on the action, and ignore extraneous visual noise. In the research paper “A Low Power, High Throughput, Fully Event-Based Stereo System<\/a>” the team reported results of 200x less power per pixel than a comparable DVS system while achieving competitive accuracies.<\/p>\n

On the software side<\/strong><\/p>\n

A new approach called BlockDrop<\/em>, that’s described in the paper “BlockDrop: Dynamic Inference Paths in Residual Networks<\/a>” enables deep learning algorithms to essentially drop layers of the neural network conditioned on the input, allowing the system to allocate resources more efficiently and accurately identify an image. In testing, BlockDrop increased recognition speed by 20%, on average, and sometimes sped up the process by as much as 36%, while maintaining the same accuracy on the ImageNet dataset.<\/p>\n

New innovations like these rethink the way today\u2019s deep learning systems can be designed in order to make them a practical reality for current and future applications.<\/p>\n

 <\/p>\n

Sign up for the free insideBIGDATA\u00a0newsletter<\/a>.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"

We’re seeing much hype in the marketplace about the potential of AI, especially with respect to computer vision systems and its ability accelerate the development of everything from self-driving cars to autonomous robots. To create more dynamic and efficient deep learning systems, that don\u2019t compromise accuracy, IBM Research is exploring new and novel computer vision techniques from both a hardware and software angle.<\/p>\n","protected":false},"author":37,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"footnotes":""},"categories":[526,87,180,173,56,84,1],"tags":[264,96],"acf":[],"yoast_head":"\nAdvancements in Dynamic and Efficient Deep Learning Systems - insideBIGDATA<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Advancements in Dynamic and Efficient Deep Learning Systems - insideBIGDATA\" \/>\n<meta property=\"og:description\" content=\"We're seeing much hype in the marketplace about the potential of AI, especially with respect to computer vision systems and its ability accelerate the development of everything from self-driving cars to autonomous robots. To create more dynamic and efficient deep learning systems, that don\u2019t compromise accuracy, IBM Research is exploring new and novel computer vision techniques from both a hardware and software angle.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/\" \/>\n<meta property=\"og:site_name\" content=\"insideBIGDATA\" \/>\n<meta property=\"article:publisher\" content=\"http:\/\/www.facebook.com\/insidebigdata\" \/>\n<meta property=\"article:published_time\" content=\"2018-06-22T15:30:47+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2018-06-23T18:05:50+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/insidebigdata.com\/wp-content\/uploads\/2017\/10\/DeepLearning_logo.jpg\" \/>\n<meta name=\"author\" content=\"Daniel Gutierrez\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@AMULETAnalytics\" \/>\n<meta name=\"twitter:site\" content=\"@insideBigData\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Daniel Gutierrez\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/\",\"url\":\"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/\",\"name\":\"Advancements in Dynamic and Efficient Deep Learning Systems - insideBIGDATA\",\"isPartOf\":{\"@id\":\"https:\/\/insidebigdata.com\/#website\"},\"datePublished\":\"2018-06-22T15:30:47+00:00\",\"dateModified\":\"2018-06-23T18:05:50+00:00\",\"author\":{\"@id\":\"https:\/\/insidebigdata.com\/#\/schema\/person\/2540da209c83a68f4f5922848f7376ed\"},\"breadcrumb\":{\"@id\":\"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/insidebigdata.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Advancements in Dynamic and Efficient Deep Learning Systems\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/insidebigdata.com\/#website\",\"url\":\"https:\/\/insidebigdata.com\/\",\"name\":\"insideBIGDATA\",\"description\":\"Your Source for AI, Data Science, Deep Learning & Machine Learning Strategies\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/insidebigdata.com\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/insidebigdata.com\/#\/schema\/person\/2540da209c83a68f4f5922848f7376ed\",\"name\":\"Daniel Gutierrez\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/insidebigdata.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/5780282e7e567e2a502233e948464542?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/5780282e7e567e2a502233e948464542?s=96&d=mm&r=g\",\"caption\":\"Daniel Gutierrez\"},\"description\":\"Daniel D. Gutierrez is a Data Scientist with Los Angeles-based AMULET Analytics, a service division of AMULET Development Corp. He's been involved with data science and Big Data long before it came in vogue, so imagine his delight when the Harvard Business Review recently deemed \\\"data scientist\\\" as the sexiest profession for the 21st century. Previously, he taught computer science and database classes at UCLA Extension for over 15 years, and authored three computer industry books on database technology. He also served as technical editor, columnist and writer at a major computer industry monthly publication for 7 years. Follow his data science musings at @AMULETAnalytics.\",\"sameAs\":[\"http:\/\/www.insidebigdata.com\",\"https:\/\/twitter.com\/@AMULETAnalytics\"],\"url\":\"https:\/\/insidebigdata.com\/author\/dangutierrez\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Advancements in Dynamic and Efficient Deep Learning Systems - insideBIGDATA","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/","og_locale":"en_US","og_type":"article","og_title":"Advancements in Dynamic and Efficient Deep Learning Systems - insideBIGDATA","og_description":"We're seeing much hype in the marketplace about the potential of AI, especially with respect to computer vision systems and its ability accelerate the development of everything from self-driving cars to autonomous robots. To create more dynamic and efficient deep learning systems, that don\u2019t compromise accuracy, IBM Research is exploring new and novel computer vision techniques from both a hardware and software angle.","og_url":"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/","og_site_name":"insideBIGDATA","article_publisher":"http:\/\/www.facebook.com\/insidebigdata","article_published_time":"2018-06-22T15:30:47+00:00","article_modified_time":"2018-06-23T18:05:50+00:00","og_image":[{"url":"https:\/\/insidebigdata.com\/wp-content\/uploads\/2017\/10\/DeepLearning_logo.jpg"}],"author":"Daniel Gutierrez","twitter_card":"summary_large_image","twitter_creator":"@AMULETAnalytics","twitter_site":"@insideBigData","twitter_misc":{"Written by":"Daniel Gutierrez","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/","url":"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/","name":"Advancements in Dynamic and Efficient Deep Learning Systems - insideBIGDATA","isPartOf":{"@id":"https:\/\/insidebigdata.com\/#website"},"datePublished":"2018-06-22T15:30:47+00:00","dateModified":"2018-06-23T18:05:50+00:00","author":{"@id":"https:\/\/insidebigdata.com\/#\/schema\/person\/2540da209c83a68f4f5922848f7376ed"},"breadcrumb":{"@id":"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/insidebigdata.com\/2018\/06\/22\/advancements-dynamic-efficient-deep-learning-systems\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/insidebigdata.com\/"},{"@type":"ListItem","position":2,"name":"Advancements in Dynamic and Efficient Deep Learning Systems"}]},{"@type":"WebSite","@id":"https:\/\/insidebigdata.com\/#website","url":"https:\/\/insidebigdata.com\/","name":"insideBIGDATA","description":"Your Source for AI, Data Science, Deep Learning & Machine Learning Strategies","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/insidebigdata.com\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/insidebigdata.com\/#\/schema\/person\/2540da209c83a68f4f5922848f7376ed","name":"Daniel Gutierrez","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/insidebigdata.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/5780282e7e567e2a502233e948464542?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/5780282e7e567e2a502233e948464542?s=96&d=mm&r=g","caption":"Daniel Gutierrez"},"description":"Daniel D. Gutierrez is a Data Scientist with Los Angeles-based AMULET Analytics, a service division of AMULET Development Corp. He's been involved with data science and Big Data long before it came in vogue, so imagine his delight when the Harvard Business Review recently deemed \"data scientist\" as the sexiest profession for the 21st century. Previously, he taught computer science and database classes at UCLA Extension for over 15 years, and authored three computer industry books on database technology. He also served as technical editor, columnist and writer at a major computer industry monthly publication for 7 years. Follow his data science musings at @AMULETAnalytics.","sameAs":["http:\/\/www.insidebigdata.com","https:\/\/twitter.com\/@AMULETAnalytics"],"url":"https:\/\/insidebigdata.com\/author\/dangutierrez\/"}]}},"jetpack_featured_media_url":"","jetpack_shortlink":"https:\/\/wp.me\/p9eA3j-5mk","jetpack-related-posts":[{"id":22567,"url":"https:\/\/insidebigdata.com\/2019\/05\/04\/accelerating-training-for-ai-deep-learning-networks-with-chunking\/","url_meta":{"origin":20604,"position":0},"title":"Accelerating Training for AI Deep Learning Networks with \u201cChunking\u201d","date":"May 4, 2019","format":false,"excerpt":"At the International Conference on Learning Representations on May 6, IBM Research will share a deeper look around how chunk-based accumulation can speed the training for deep learning networks used for artificial intelligence (AI).","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2019\/05\/Deep_Learning_shutterstock_386816095.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":19576,"url":"https:\/\/insidebigdata.com\/2017\/12\/13\/interview-vivienne-sze-associate-professor-electrical-engineering-computer-science-mit\/","url_meta":{"origin":20604,"position":1},"title":"Interview: Vivienne Sze, Associate Professor of Electrical Engineering and Computer Science at MIT","date":"December 13, 2017","format":false,"excerpt":"I recently caught up with Vivienne Sze, Associate Professor of Electrical Engineering and Computer Science at MIT, to discuss the launch a new professional education course titled, \"Designing Efficient Deep Learning Systems.\" The two-day class will run March 28-29, 2018 at the Samsung Campus in Mountain View, CA and will\u2026","rel":"","context":"In "Academic"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2017\/12\/Vivienne-Sze.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":22263,"url":"https:\/\/insidebigdata.com\/2019\/03\/15\/best-of-arxiv-org-for-ai-machine-learning-and-deep-learning-february-2019\/","url_meta":{"origin":20604,"position":2},"title":"Best of arXiv.org for AI, Machine Learning, and Deep Learning \u2013 February 2019","date":"March 15, 2019","format":false,"excerpt":"In this recurring monthly feature, we will filter all the recent research papers appearing in the arXiv.org preprint server for subjects relating to AI, machine learning and deep learning \u2013 from disciplines including statistics, mathematics and computer science \u2013 and provide you with a useful \u201cbest of\u201d list for the\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2013\/12\/arxiv.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":19404,"url":"https:\/\/insidebigdata.com\/2017\/11\/17\/ibm-introduces-new-software-ease-adoption-ai-machine-learning-deep-learning\/","url_meta":{"origin":20604,"position":3},"title":"IBM Introduces New Software to Ease Adoption of AI, Machine Learning and Deep Learning","date":"November 17, 2017","format":false,"excerpt":"IBM announced new software to deliver faster time to insight for high performance data analytics (HPDA) workloads, such as Spark, Tensor Flow and Caff\u00e9, for AI, Machine Learning and Deep Learning. Based on the same software, which will be deployed for the Department of Energy\u2019s CORAL Supercomputer Project at both\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":22660,"url":"https:\/\/insidebigdata.com\/2019\/05\/19\/uc-berkeley-graduate-receives-acm-doctoral-dissertation-award\/","url_meta":{"origin":20604,"position":4},"title":"UC Berkeley Graduate Receives ACM Doctoral Dissertation Award","date":"May 19, 2019","format":false,"excerpt":"ACM, the Association for Computing Machinery, announced that Chelsea Finn receives the 2018 ACM Doctoral Dissertation Award for her dissertation, \u201cLearning to Learn with Gradients.\u201d In her thesis, Finn introduced algorithms for meta-learning that enable deep networks to solve new tasks from small data sets, and demonstrated how her algorithms\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2019\/05\/ACM_logo.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":17860,"url":"https:\/\/insidebigdata.com\/2017\/05\/15\/how-traditional-industries-are-using-machine-learning-and-deep-learning-to-gain-strategic-business-insights\/","url_meta":{"origin":20604,"position":5},"title":"How Traditional Industries Are Using Machine Learning and Deep Learning to Gain Strategic Business Insights","date":"May 15, 2017","format":false,"excerpt":"Many enterprises are now embracing an accelerated path for accessing, and processing, and using data through machine learning. This article is part of a full report that explores trends in machine learning and deep learning.","rel":"","context":"In "Featured"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2017\/04\/Dell_Nivida_ML_DLguide.jpg?resize=350%2C200","width":350,"height":200},"classes":[]}],"_links":{"self":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/posts\/20604"}],"collection":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/users\/37"}],"replies":[{"embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/comments?post=20604"}],"version-history":[{"count":0,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/posts\/20604\/revisions"}],"wp:attachment":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/media?parent=20604"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/categories?post=20604"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/tags?post=20604"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}