BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Australia/Brisbane BEGIN:STANDARD DTSTART:19920301T020000 TZOFFSETFROM:+1100 TZOFFSETTO:+1000 TZNAME:AEST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20150625T031408Z UID:3AED6B68-1AE5-11E5-A923-0050568D2FB3 DTSTART;TZID=Australia/Brisbane:20150707T180000 DTEND;TZID=Australia/Brisbane:20150707T200000 DESCRIPTION:This month's paper is:\n\nDeep learning\, Yann LeCun\, Yoshua B engio & Geoffrey Hinton\, Nature 521\, 436–444 (28 May 2015) doi:10.1038 /nature14539\n\nKristian Weegink has kindly agreed to lead the discussion and the venue will again be the Brisbane Brewhouse (see address details & map below).\n\n*About the 1st Tuesday Journal-Paper Club:* the idea is to meet regularly\, usually on the 1st Tuesday of the month as the name sugge sts (inspired by the ABC TV series "1st Tuesday Book Club"). Each month\, the participants would agree on a highly cited\, 'top ten' or major-prize- winning article in an SPS or ComSoc journal (but not one of our own!). We would also select a Discussion Leader. Through the month\, each of the par ticipants would read the article. At the next meeting\, the Discussion Lea der would lead a discussion of that article\, starting with his/her own ap praisal. In this way\, it is hoped that we could all broaden our understan ding of the field and further develop a sense of community. 1st rule of 1s t Tuesday Journal-Paper Club: tell everyone about 1st Tuesday Journal-Pape r Club.\n\nSpeaker(s): \, \, \, \n\nAgenda: \nIn this month's session we c an discuss this very recent nature paper on deep learning AND the strategi es utlised to publish engineering and computer science papers in high impa ct outlets\, such as Nature.\n\nAbstract\n\nDeep learning allows computati onal models that are composed of multiple processing layers to learn repre sentations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech rec- ognition\, visu al object recognition\, object detection and many other domains such as dr ug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a m achine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer . Deep convolutional nets have brought about breakthroughs in processing i mages\, video\, speech and audio\, whereas recurrent nets have shone light on sequential data such as text and speech.\n\nBldg: Brewhouse Brisbane\, 601 Stanley St.\, Woolloongabba\, Queensland\, Australia\, 4102 LOCATION:Bldg: Brewhouse Brisbane\, 601 Stanley St.\, Woolloongabba\, Queen sland\, Australia\, 4102 ORGANIZER:a.bradley@itee.uq.edu.au SEQUENCE:2 SUMMARY:1st Tuesday Journal-Paper Club: July 2015 meeting URL;VALUE=URI:https://events.vtools.ieee.org/m/35109 X-ALT-DESC:Description: <br /><p>This month's paper is:</p>\n<p>Deep learni ng\, Yann LeCun\, Yoshua Bengio &amp\; Geoffrey Hinton\, Nature 521\, 436& ndash\;444 (28 May 2015) doi:10.1038/nature14539</p>\n<p>Kristian Weegink& nbsp\;has kindly agreed to lead the discussion and the venue will again be the Brisbane Brewhouse (see address details &amp\; map below).</p>\n<p>*A bout the 1st Tuesday Journal-Paper Club:* the idea is to meet regularly\, usually on the 1st Tuesday of the month as the name suggests (inspired by the ABC TV series "1st Tuesday Book Club"). Each month\, the participants would agree on a highly cited\, 'top ten' or major-prize-winning article i n an SPS or ComSoc journal (but not one of our own!). We would also select a Discussion Leader. Through the month\, each of the participants would r ead the article. At the next meeting\, the Discussion Leader would lead a discussion of that article\, starting with his/her own appraisal. In this way\, it is hoped that we could all broaden our understanding of the field and further develop a sense of community. 1st rule of 1st Tuesday Journal -Paper Club: tell everyone about 1st Tuesday Journal-Paper Club.</p>\n<p>& nbsp\;</p>\n<p>&nbsp\;</p><br /><br />Agenda: <br /><p>&nbsp\;</p>\n<div c lass="page" title="Page 1">\n<div class="section">\n<div class="layoutArea ">\n<div class="column">\n<p>In this month's session we can discuss this v ery recent nature paper on deep learning AND the strategies utlised to pub lish engineering and computer science papers in high impact outlets\, such as Nature.</p>\n<p>Abstract&nbsp\;</p>\n<p>Deep learning allows computati onal models that are composed of multiple processing layers to learn repre sentations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech rec- ognition\, visu al object recognition\, object detection and many other domains such as dr ug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a m achine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer . Deep convolutional nets have brought about breakthroughs in processing i mages\, video\, speech and audio\, whereas recurrent nets have shone light on sequential data such as text and speech.</p>\n</div>\n</div>\n</div>\n </div>\n<p>&nbsp\;</p>\n<p>&nbsp\;</p>\n<p>&nbsp\;</p> END:VEVENT END:VCALENDAR