BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Pacific BEGIN:DAYLIGHT DTSTART:20180311T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20181104T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20181011T043816Z UID:5123CF7B-0E56-4327-8DD8-65D433F3651D DTSTART;TZID=US/Pacific:20180921T130000 DTEND;TZID=US/Pacific:20180921T170000 DESCRIPTION:IEEE Circuits and Systems Society-Silicon Valley (CAS-SV) Artif icial Intelligent For Industry Forum\n\nTopic: Algorithm-architecture co-d esign for energy-efficient deep learning\, including algorithm optimizatio n (e.g.\, novel numerical representation\, network pruning/compression) an d accelerator architectures (e.g.\, programmable SoC).\n\nSpeakers:\n\n(1) Dr. Pradeep Dubey from Parallel Computing Lab\, Intel Labs\, Intel Corpor ation (IEEE Fellow and Intel Fellow)\n\n(2) Prof. Vivienne Sze from MIT\, Associate Professor of Electrical Engineering and Computer Science\, Elect rical Engineering and Computer Science\, (http://www.rle.mit.edu/people/di rectory/vivienne-sze/)\n\n(3) Prof. Yung-Hsiang Lu from Purdue University\ , Professor in the School of Electrical and Computer Engineering (ACM dist inguished speaker) (https://engineering.purdue.edu/ECE/People/ptProfile?re source_id=3355&group_id=2571)\n\n(4) Dr. Mark Sandler\, Google\n\nTitle: M obileNet: designing efficient architectures for mobile classification\, de tection and segmentation.\n\nAbstract: In this talk we present lessons and insights that led us to design of MobileNet V1 and V2\, discuss\n\ncommon optimization techniques\, such as quantization\, and common pitfalls when designing\n\nefficient architectures as well show our insights can guide automated architecture search.\n\nBio: Mark Sandler is a research scientis t at Google\, working among other things\,\n\non next generation high perf ormance neural networks for mobile vision.\n\nHost:\n\nIEEE Circuits and S ystems Society and Intel Corporation\n\nCo-Host: IEEE Circuits and Systems Society Santa Clara Valley Chapter\, IEEE Signal Processing Society Santa Clara Valley Chapter\, and IEEE Computer Society Technical Committee on M ultimedia Computing\n\nCo-sponsored by: IEEE CAS Society\, IEEE Signal Pro cessing Society Chapter (Santa Clara Valley)\n\nSpeaker(s): Dr. Pradeep Du bey\, Prof. Vivienne Sze\n\nBldg: SC12 auditorium\, Intel Santa Clara \, 3 600 Juliette Ln\, Santa Clara\, California\, United States\, 95054 LOCATION:Bldg: SC12 auditorium\, Intel Santa Clara \, 3600 Juliette Ln\, Sa nta Clara\, California\, United States\, 95054 ORGANIZER:imran.bashir@ieee.org SEQUENCE:1 SUMMARY:IEEE CASS-SV Artificial Intelligent For Industry Forum URL;VALUE=URI:https://events.vtools.ieee.org/m/176123 X-ALT-DESC:Description: <br /><p><strong>IEEE Circuits and Systems Society- Silicon Valley (CAS-SV) Artificial Intelligent For Industry Forum</strong> </p>\n<p>Topic: Algorithm-architecture co-design for energy-efficient deep learning\, including algorithm optimization (e.g.\, novel numerical repre sentation\, network pruning/compression) and accelerator architectures (e. g.\, programmable SoC).</p>\n<p>Speakers:</p>\n<p>(1)&nbsp\;Dr. Pradeep Du bey from Parallel Computing Lab\, Intel Labs\, Intel Corporation (IEEE Fel low and Intel Fellow)</p>\n<p>(2) Prof. Vivienne Sze from MIT\, Associate Professor of Electrical Engineering and Computer Science\, Electrical Engi neering and Computer Science\, (<a href="http://www.rle.mit.edu/people/dir ectory/vivienne-sze/">http://www.rle.mit.edu/people/directory/vivienne-sze /</a>)</p>\n<p>(3)&nbsp\;Prof. Yung-Hsiang Lu from Purdue University\, Pro fessor in the School of Electrical and Computer Engineering (ACM distingui shed speaker) (<a href="https://engineering.purdue.edu/ECE/People/ptProfil e?resource_id=3355&amp\;group_id=2571">https://engineering.purdue.edu/ECE/ People/ptProfile?resource_id=3355&amp\;group_id=2571</a>)</p>\n<p>(4)&nbsp \;Dr. Mark Sandler\, Google</p>\n<p>Title: MobileNet: designing efficient architectures for mobile classification\, detection and segmentation.</p>\ n<p>Abstract: In this talk we present lessons and insights that led us to design of MobileNet V1 and V2\, discuss</p>\n<p>common optimization techni ques\, such as quantization\, and common pitfalls when designing</p>\n<p>e fficient architectures as well show our insights can guide automated archi tecture search.</p>\n<p>Bio: Mark Sandler is a research scientist at Googl e\, working among other things\,</p>\n<p>on next generation high performan ce neural networks for mobile vision.</p>\n<p>Host:</p>\n<p>IEEE Circuits and Systems Society and Intel Corporation</p>\n<p>Co-Host: IEEE Circuits a nd Systems Society Santa Clara Valley Chapter\, IEEE Signal Processing Soc iety Santa Clara Valley Chapter\, and IEEE Computer Society Technical Comm ittee on Multimedia Computing</p> END:VEVENT END:VCALENDAR