BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Pacific BEGIN:DAYLIGHT DTSTART:20190310T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20191103T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20190907T034913Z UID:58F118AF-555C-41EE-B758-4B95819E376A DTSTART;TZID=US/Pacific:20190906T130000 DTEND;TZID=US/Pacific:20190906T170000 DESCRIPTION:CASS-SCV Artificial Intelligence for Industry (AI4I) Forum - Fa ll 2019\n\nEvent sponsored and organized by:\n\n[IEEE Circuits and Systems Society (CASS)](https://www.ieee-cas.org/)\n\nCo-sponsors:\n\n- [Circuits and Systems Society - Santa Clara Valley Chapter (CASS-SCV)](http://sites .ieee.org/scv-cas/)\n- [Computer Society (CS)](http://computer.ieeesilicon valley.org/)\n- [Computational Intelligence Society (CIS)](https://ieee-re gion6.org/scv-cis/)\n- [Solid-State Circuits Society(SSCS)](http://sites.i eee.org/scv-sscs/upcoming-events/)\n- [Signal Processing Society(SPS)](htt ps://ewh.ieee.org/r6/scv/sps/)\n- [Communication Society (ComSoC)](https:/ /www.meetup.com/IEEE-ComSoc-SCV/)\n\nDATE & TIME:\n\nFriday\, September 6t h\, 2019. 1 PM - 5 PM\n\nPROGRAM:\n\n1:00 - 1:30 PM Check-in / Networking & Refreshments\n\n1:30 - 2:15 PM Prof. S.Y. Kung (Princeton)\n\n2:15 - 3:0 0 PM Pete Warden (Google)\n\n3:30 - 4:15 PM TBD\n\n4:15 - 5:00 PM TBD\n\n5 :00 PM Adjourn\n\nLOCATION:\n\nIntel SC-9 Auditorium\n\n2191 Laurelwood Rd \, Santa Clara\, CA 95054 (Northwest corner of 101 & Montague Expwy)\n\nAG ENDA:\n\n1:30 - 2:15 PM Prof. S.Y. Kung (Princeton)\n\nTITLE: From Deep Le arning to X-Learning: An Internal and Explainable Learning for XAI\n\nABST RACT: The success of deep Learning (or AI2.0) depends solely on Back-propa gation (BP)\, a external learning paradigm\, whose supervision is exclusiv ely accessed via the external interfacing nodes (i.e. input/output neurons ). As such\, Deep Learning has been limited to the parameter training of t he neural nets (NNs). The important task of designing optimal net structur es has to resort to trial and error. Therefore\, we shall design an Xnet w hich may be use to simultaneously train the structure and parameters of th e net. In addition\, it can facilitate Internal Neuron's Explainablility s o as to fully support DARPA's Explainable AI (i.e. XAI or AI3.0). Our inte rnal learning paradigm leads to an Explainable Neural Networks (Xnet) comp rising (1) internal teacher labels (ITL) and (2) internal optimization met rics (IOM). X-learning allows us to effectively rank the internal neurons (hidden nodes) and thus sets the footing for the notion of structural grad ient and structural learning.\n\nPursuant to our simulation studies\, Xnet can simultaneously compress the structure and raise the accuracy. There i s evidence supporting that it may outperform many popular pruning/compress ion methods. Most importantly\, X-learning opens up promising research fro nts on (1) explainable learning models for XAI and (2) machine-to-machine mutual learning which will become appealing in the 5G era\n\nBIO: S.Y. Kun g\, Life Fellow of IEEE\, is a Professor at Department of Electrical Engin eering in Princeton University. His research areas include multimedia info rmation processing\, machine learning\, systematic design of deep learning networks\, VLSI array processors\, and compressive privacy. He was a foun ding member of several Technical Committees (TC) of the IEEE Signal Proces sing Society. He was elected to Fellow in 1988 and served as a Member of t he Board of Governors of the IEEE Signal Processing Society (1989-1991). H e was a recipient of IEEE Signal Processing Society's Technical Achievemen t Award for the contributions on "parallel processing and neural network a lgorithms for signal processing" (1992)\; a Distinguished Lecturer of IEEE Signal Processing Society (1994)\; a recipient of IEEE Signal Processing Society's Best Paper Award\; and a recipient of the IEEE Third Millennium Medal (2000). Since 1990\, he has been the Editor-In-Chief of the Journal of VLSI Signal Processing Systems. He has authored and co-authored more th an 500 technical publications and numerous textbooks including ``VLSI Arra y Processors''\, Prentice-Hall (1988)\; ``Digital Neural Networks''\, Pren tice-Hall (1993) \; ``Principal Component Neural Networks''\, John-Wiley ( 1996)\; ``Biometric Authentication: A Machine Learning Approach''\, Prenti ce-Hall (2004)\; and ``Kernel Methods and Machine Learning”\, Cambridge University Press (2014).\n\n2:15 - 3:00 PM Pete Warden (Google)\n\nTITLE:\ nABSTRACT:\n\nBIO:\n\n3:30 - 4:15 PM TBD\n\nTITLE:\n\nABSTRACT:\n\nBIO:\n\ n4:15 - 5:00 PM TBD\n\nTITLE:\n\nABSTRACT:\n\nBIO:\n\nCo-sponsored by: Sol id State Circuits Society (SSCS)\, Computer Society (CS)\, Computational I ntelligence Society\n\nAgenda: \nCASS-SCV Artificial Intelligence for Indu stry (AI4I) Forum - Fall 2019\n\nEvent sponsored and organized by:\n\n[IEE E Circuits and Systems Society (CASS)](https://www.ieee-cas.org/)\n\nCo-sp onsors:\n\n- [Circuits and Systems Society - Santa Clara Valley Chapter (C ASS-SCV)](http://sites.ieee.org/scv-cas/)\n- [Computer Society (CS)](http: //computer.ieeesiliconvalley.org/)\n- [Computational Intelligence Society (CIS)](https://ieee-region6.org/scv-cis/)\n- [Solid-State Circuits Society (SSCS)](http://sites.ieee.org/scv-sscs/upcoming-events/)\n- [Signal Proces sing Society(SPS)](https://ewh.ieee.org/r6/scv/sps/)\n- [Communication Soc iety (ComSoC)](https://www.meetup.com/IEEE-ComSoc-SCV/)\n\nDATE & TIME:\n\ nFriday\, September 6th\, 2019. 1 PM - 5 PM\n\nPROGRAM:\n\n1:00 - 1:30 PM Check-in / Networking & Refreshments\n\n1:30 - 2:15 PM Prof. S.Y. Kung (Pr inceton)\n\n2:15 - 3:00 PM Pete Warden (Google)\n\n3:30 - 4:15 PM TBD\n\n4 :15 - 5:00 PM TBD\n\n5:00 PM Adjourn\n\nLOCATION:\n\nIntel SC-9 Auditorium \n\n2191 Laurelwood Rd\, Santa Clara\, CA 95054 (Northwest corner of 101 & Montague Expwy)\n\nAGENDA:\n\n1:30 - 2:15 PM Prof. S.Y. Kung (Princeton)\ n\nTITLE: From Deep Learning to X-Learning: An Internal and Explainable Le arning for XAI\n\nABSTRACT: The success of deep Learning (or AI2.0) depend s solely on Back-propagation (BP)\, a external learning paradigm\, whose s upervision is exclusively accessed via the external interfacing nodes (i.e . input/output neurons). As such\, Deep Learning has been limited to the p arameter training of the neural nets (NNs). The important task of designin g optimal net structures has to resort to trial and error. Therefore\, we shall design an Xnet which may be use to simultaneously train the structur e and parameters of the net. In addition\, it can facilitate Internal Neur on's Explainablility so as to fully support DARPA's Explainable AI (i.e. X AI or AI3.0). Our internal learning paradigm leads to an Explainable Neura l Networks (Xnet) comprising (1) internal teacher labels (ITL) and (2) int ernal optimization metrics (IOM). X-learning allows us to effectively rank the internal neurons (hidden nodes) and thus sets the footing for the not ion of structural gradient and structural learning.\n\nPursuant to our sim ulation studies\, Xnet can simultaneously compress the structure and raise the accuracy. There is evidence supporting that it may outperform many po pular pruning/compression methods. Most importantly\, X-learning opens up promising research fronts on (1) explainable learning models for XAI and ( 2) machine-to-machine mutual learning which will become appealing in the 5 G era\n\nBIO: S.Y. Kung\, Life Fellow of IEEE\, is a Professor at Departme nt of Electrical Engineering in Princeton University. His research areas i nclude multimedia information processing\, machine learning\, systematic d esign of deep learning networks\, VLSI array processors\, and compressive privacy. He was a founding member of several Technical Committees (TC) of the IEEE Signal Processing Society. He was elected to Fellow in 1988 and s erved as a Member of the Board of Governors of the IEEE Signal Processing Society (1989-1991). He was a recipient of IEEE Signal Processing Society' s Technical Achievement Award for the contributions on "parallel processin g and neural network algorithms for signal processing" (1992)\; a Distingu ished Lecturer of IEEE Signal Processing Society (1994)\; a recipient of I EEE Signal Processing Society's Best Paper Award\; and a recipient of the IEEE Third Millennium Medal (2000). Since 1990\, he has been the Editor-In -Chief of the Journal of VLSI Signal Processing Systems. He has authored a nd co-authored more than 500 technical publications and numerous textbooks including ``VLSI Array Processors''\, Prentice-Hall (1988)\; ``Digital Ne ural Networks''\, Prentice-Hall (1993) \; ``Principal Component Neural Net works''\, John-Wiley (1996)\; ``Biometric Authentication: A Machine Learni ng Approach''\, Prentice-Hall (2004)\; and ``Kernel Methods and Machine Le arning”\, Cambridge University Press (2014).\n\n2:15 - 3:00 PM Pete Ward en (Google)\n\nTITLE:\nABSTRACT:\n\nBIO:\n\n3:30 - 4:15 PM TBD\n\nTITLE:\n \nABSTRACT:\n\nBIO:\n\n4:15 - 5:00 PM TBD\n\nTITLE:\n\nABSTRACT:\n\nBIO:\n \nBldg: Intel SC-9 Auditorium\, Intel SC-9 Auditorium\, 2191 Laurelwood Rd \, Santa Clara\, California\, United States\, 95054 LOCATION:Bldg: Intel SC-9 Auditorium\, Intel SC-9 Auditorium\, 2191 Laurelw ood Rd\, Santa Clara\, California\, United States\, 95054 ORGANIZER:imran.bashir@ieee.org SEQUENCE:1 SUMMARY:CASS-SCV Artificial Intelligence for Industry (AI4I) Forum – Fall 2019 URL;VALUE=URI:https://events.vtools.ieee.org/m/201910 X-ALT-DESC:Description: <br /><h2 style="font-weight: 600\;"><strong>CASS-S CV Artificial Intelligence for Industry (AI4I) Forum - Fall 2019</strong>< /h2>\n<p style="font-weight: 400\;">Event sponsored and organized by:</p>\ n<p style="font-weight: 400\;"><a href="https://www.ieee-cas.org/">IEEE Ci rcuits and Systems Society (CASS)</a></p>\n<p style="font-weight: 400\;">C o-sponsors:</p>\n<ul style="font-weight: 400\;">\n<li><a href="http://site s.ieee.org/scv-cas/">Circuits and Systems Society - Santa Clara Valley Cha pter (CASS-SCV)</a></li>\n<li><a href="http://computer.ieeesiliconvalley.o rg/">Computer Society (CS)</a></li>\n<li><a href="https://ieee-region6.org /scv-cis/">Computational Intelligence Society&nbsp\;(CIS)</a></li>\n<li><a href="http://sites.ieee.org/scv-sscs/upcoming-events/">Solid-State Circui ts Society(SSCS)</a></li>\n<li><a href="https://ewh.ieee.org/r6/scv/sps/"> Signal Processing Society(SPS)</a></li>\n<li><a href="https://www.meetup.c om/IEEE-ComSoc-SCV/">Communication Society (ComSoC)</a></li>\n</ul>\n<h2 s tyle="font-weight: 600\;">DATE &amp\; TIME:</h2>\n<p style="font-weight: 4 00\;">Friday\, September 6th\, 2019. 1 PM - 5 PM</p>\n<h2 style="font-weig ht: 600\;">PROGRAM:</h2>\n<p style="font-weight: 400\;">1:00 - 1:30 PM Che ck-in / Networking &amp\; Refreshments</p>\n<p style="font-weight: 400\;"> 1:30 - 2:15 PM Prof.&nbsp\;S.Y. Kung (Princeton)</p>\n<p style="font-weigh t: 400\;">2:15 - 3:00 PM Pete Warden&nbsp\;(Google)</p>\n<p style="font-we ight: 400\;">3:30 - 4:15 PM TBD</p>\n<p style="font-weight: 400\;">4:15 - 5:00 PM TBD</p>\n<p style="font-weight: 400\;">5:00 PM Adjourn</p>\n<h2 st yle="font-weight: 600\;">LOCATION:</h2>\n<p style="font-weight: 400\;">Int el SC-9 Auditorium</p>\n<p style="font-weight: 400\;">2191 Laurelwood Rd\, Santa Clara\, CA 95054 (Northwest corner of 101 &amp\; Montague Expwy)</p >\n<h2 style="font-weight: 600\;">AGENDA:</h2>\n<p style="font-weight: 400 \;"><strong>1:30 - 2:15 PM Prof.&nbsp\;S.Y. Kung (Princeton)</strong></p>\ n<p style="font-weight: 400\;"><strong>TITLE:</strong>&nbsp\;From Deep Lea rning to X-Learning: An Internal and Explainable Learning for XAI</p>\n<p style="font-weight: 400\;"><strong>ABSTRACT:</strong>&nbsp\;The success of deep Learning (or AI2.0) depends solely on Back-propagation (BP)\, a exte rnal learning paradigm\, whose supervision is exclusively accessed via the external interfacing nodes (i.e. input/output neurons). As such\, Deep Le arning has been limited to the parameter training of the neural nets (NNs) . The important task of designing optimal net structures has to resort to trial and error. Therefore\, we shall design an Xnet which may be use to s imultaneously train the structure and parameters of the net. In addition\, it can facilitate Internal Neuron's Explainablility so as to fully suppor t DARPA's Explainable AI (i.e. XAI or AI3.0). Our internal learning paradi gm leads to an Explainable Neural Networks (Xnet) comprising (1) internal teacher labels (ITL) and (2) internal optimization metrics (IOM). X-learni ng allows us to effectively rank the internal neurons (hidden nodes) and t hus sets the footing for the notion of structural gradient and structural learning.</p>\n<p style="font-weight: 400\;">Pursuant to our simulation st udies\, Xnet can simultaneously compress the structure and raise the accur acy. There is evidence supporting that it may outperform many popular prun ing/compression methods. Most importantly\, X-learning opens up promising research fronts on (1) explainable learning models for XAI and (2) machine -to-machine mutual learning which will become appealing in the 5G era</p>\ n<p style="font-weight: 400\;"><strong>BIO:</strong>&nbsp\;S.Y. Kung\, Lif e Fellow of IEEE\, is a Professor at Department of Electrical Engineering in Princeton University. His research areas include multimedia information processing\, machine learning\, systematic design of deep learning networ ks\, VLSI array processors\, and compressive privacy. He was a founding me mber of several Technical Committees (TC) of the IEEE Signal Processing So ciety. He was elected to Fellow in 1988 and served as a Member of the Boar d of Governors of the IEEE Signal Processing Society (1989-1991). He was a recipient of IEEE Signal Processing Society's Technical Achievement Award for the contributions on "parallel processing and neural network algorith ms for signal processing" (1992)\; a Distinguished Lecturer of IEEE Signal Processing Society (1994)\; a recipient of IEEE Signal Processing Society 's Best Paper Award\; and a recipient of the IEEE Third Millennium Medal ( 2000). Since 1990\, he has been the Editor-In-Chief of the Journal of VLSI Signal Processing Systems. He has authored and co-authored more than 500 technical publications and numerous textbooks including ``VLSI Array Proce ssors''\, Prentice-Hall (1988)\; ``Digital Neural Networks''\, Prentice-Ha ll (1993) \; ``Principal Component Neural Networks''\, John-Wiley (1996)\; ``Biometric Authentication: A Machine Learning Approach''\, Prentice-Hall (2004)\; and ``Kernel Methods and Machine Learning&rdquo\;\, Cambridge Un iversity Press (2014).</p>\n<p style="font-weight: 400\;"><strong>2:15 - 3 :00 PM Pete Warden (Google)</strong></p>\n<p style="font-weight: 400\;"><s trong>TITLE:&nbsp\;</strong><strong><br />ABSTRACT:&nbsp\;</strong></p>\n< p style="font-weight: 400\;"><strong>BIO:</strong>&nbsp\;</p>\n<p style="f ont-weight: 400\;"><strong>3:30 - 4:15 PM TBD</strong></p>\n<p style="font -weight: 400\;"><strong>TITLE:</strong></p>\n<p style="font-weight: 400\;" ><strong>ABSTRACT:</strong></p>\n<p style="font-weight: 400\;"><strong>BIO :</strong>&nbsp\;</p>\n<p style="font-weight: 400\;"><strong>4:15 - 5:00 P M TBD</strong></p>\n<p style="font-weight: 400\;"><strong>TITLE:</strong>< /p>\n<p style="font-weight: 400\;"><strong>ABSTRACT:</strong></p>\n<p styl e="font-weight: 400\;"><strong>BIO:</strong></p><br /><br />Agenda: <br /> <h2 style="font-weight: 600\;"><strong>CASS-SCV Artificial Intelligence fo r Industry (AI4I) Forum - Fall 2019</strong></h2>\n<p style="font-weight: 400\;">Event sponsored and organized by:</p>\n<p style="font-weight: 400\; "><a href="https://www.ieee-cas.org/">IEEE Circuits and Systems Society (C ASS)</a></p>\n<p style="font-weight: 400\;">Co-sponsors:</p>\n<ul style="f ont-weight: 400\;">\n<li><a href="http://sites.ieee.org/scv-cas/">Circuits and Systems Society - Santa Clara Valley Chapter (CASS-SCV)</a></li>\n<li ><a href="http://computer.ieeesiliconvalley.org/">Computer Society (CS)</a ></li>\n<li><a href="https://ieee-region6.org/scv-cis/">Computational Inte lligence Society&nbsp\;(CIS)</a></li>\n<li><a href="http://sites.ieee.org/ scv-sscs/upcoming-events/">Solid-State Circuits Society(SSCS)</a></li>\n<l i><a href="https://ewh.ieee.org/r6/scv/sps/">Signal Processing Society(SPS )</a></li>\n<li><a href="https://www.meetup.com/IEEE-ComSoc-SCV/">Communic ation Society (ComSoC)</a></li>\n</ul>\n<h2 style="font-weight: 600\;">DAT E &amp\; TIME:</h2>\n<p style="font-weight: 400\;">Friday\, September 6th\ , 2019. 1 PM - 5 PM</p>\n<h2 style="font-weight: 600\;">PROGRAM:</h2>\n<p style="font-weight: 400\;">1:00 - 1:30 PM Check-in / Networking &amp\; Ref reshments</p>\n<p style="font-weight: 400\;">1:30 - 2:15 PM Prof.&nbsp\;S. Y. Kung (Princeton)</p>\n<p style="font-weight: 400\;">2:15 - 3:00 PM Pete Warden&nbsp\;(Google)</p>\n<p style="font-weight: 400\;">3:30 - 4:15 PM T BD</p>\n<p style="font-weight: 400\;">4:15 - 5:00 PM TBD</p>\n<p style="fo nt-weight: 400\;">5:00 PM Adjourn</p>\n<h2 style="font-weight: 600\;">LOCA TION:</h2>\n<p style="font-weight: 400\;">Intel SC-9 Auditorium</p>\n<p st yle="font-weight: 400\;">2191 Laurelwood Rd\, Santa Clara\, CA 95054 (Nort hwest corner of 101 &amp\; Montague Expwy)</p>\n<h2 style="font-weight: 60 0\;">AGENDA:</h2>\n<p style="font-weight: 400\;"><strong>1:30 - 2:15 PM Pr of.&nbsp\;S.Y. Kung (Princeton)</strong></p>\n<p style="font-weight: 400\; "><strong>TITLE:</strong>&nbsp\;From Deep Learning to X-Learning: An Inter nal and Explainable Learning for XAI</p>\n<p style="font-weight: 400\;"><s trong>ABSTRACT:</strong>&nbsp\;The success of deep Learning (or AI2.0) dep ends solely on Back-propagation (BP)\, a external learning paradigm\, whos e supervision is exclusively accessed via the external interfacing nodes ( i.e. input/output neurons). As such\, Deep Learning has been limited to th e parameter training of the neural nets (NNs). The important task of desig ning optimal net structures has to resort to trial and error. Therefore\, we shall design an Xnet which may be use to simultaneously train the struc ture and parameters of the net. In addition\, it can facilitate Internal N euron's Explainablility so as to fully support DARPA's Explainable AI (i.e . XAI or AI3.0). Our internal learning paradigm leads to an Explainable Ne ural Networks (Xnet) comprising (1) internal teacher labels (ITL) and (2) internal optimization metrics (IOM). X-learning allows us to effectively r ank the internal neurons (hidden nodes) and thus sets the footing for the notion of structural gradient and structural learning.</p>\n<p style="font -weight: 400\;">Pursuant to our simulation studies\, Xnet can simultaneous ly compress the structure and raise the accuracy. There is evidence suppor ting that it may outperform many popular pruning/compression methods. Most importantly\, X-learning opens up promising research fronts on (1) explai nable learning models for XAI and (2) machine-to-machine mutual learning w hich will become appealing in the 5G era</p>\n<p style="font-weight: 400\; "><strong>BIO:</strong>&nbsp\;S.Y. Kung\, Life Fellow of IEEE\, is a Profe ssor at Department of Electrical Engineering in Princeton University. His research areas include multimedia information processing\, machine learnin g\, systematic design of deep learning networks\, VLSI array processors\, and compressive privacy. He was a founding member of several Technical Com mittees (TC) of the IEEE Signal Processing Society. He was elected to Fell ow in 1988 and served as a Member of the Board of Governors of the IEEE Si gnal Processing Society (1989-1991). He was a recipient of IEEE Signal Pro cessing Society's Technical Achievement Award for the contributions on "pa rallel processing and neural network algorithms for signal processing" (19 92)\; a Distinguished Lecturer of IEEE Signal Processing Society (1994)\; a recipient of IEEE Signal Processing Society's Best Paper Award\; and a r ecipient of the IEEE Third Millennium Medal (2000). Since 1990\, he has be en the Editor-In-Chief of the Journal of VLSI Signal Processing Systems. H e has authored and co-authored more than 500 technical publications and nu merous textbooks including ``VLSI Array Processors''\, Prentice-Hall (1988 )\; ``Digital Neural Networks''\, Prentice-Hall (1993) \; ``Principal Comp onent Neural Networks''\, John-Wiley (1996)\; ``Biometric Authentication: A Machine Learning Approach''\, Prentice-Hall (2004)\; and ``Kernel Method s and Machine Learning&rdquo\;\, Cambridge University Press (2014).</p>\n< p style="font-weight: 400\;"><strong>2:15 - 3:00 PM Pete Warden (Google)</ strong></p>\n<p style="font-weight: 400\;"><strong>TITLE:&nbsp\;</strong>< strong><br />ABSTRACT:&nbsp\;</strong></p>\n<p style="font-weight: 400\;"> <strong>BIO:</strong>&nbsp\;</p>\n<p style="font-weight: 400\;"><strong>3: 30 - 4:15 PM TBD</strong></p>\n<p style="font-weight: 400\;"><strong>TITLE :</strong></p>\n<p style="font-weight: 400\;"><strong>ABSTRACT:</strong></ p>\n<p style="font-weight: 400\;"><strong>BIO:</strong>&nbsp\;</p>\n<p sty le="font-weight: 400\;"><strong>4:15 - 5:00 PM TBD</strong></p>\n<p style= "font-weight: 400\;"><strong>TITLE:</strong></p>\n<p style="font-weight: 4 00\;"><strong>ABSTRACT:</strong></p>\n<p style="font-weight: 400\;"><stron g>BIO:</strong></p> END:VEVENT END:VCALENDAR