BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Central BEGIN:DAYLIGHT DTSTART:20220313T030000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20211107T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20211208T220709Z UID:87AD5913-1436-45B8-B07E-AFF0168EED22 DTSTART;TZID=US/Central:20211208T140000 DTEND;TZID=US/Central:20211208T150000 DESCRIPTION:Northwestern ECE Distinguished Seminar Series\n\nDetailed Infor mation: https://www.mccormick.northwestern.edu/electrical-computer/news-ev ents/events/\n\nProfessor J. Joshua Yang\, University of Southern Californ ia\n\nCMOS technology has been the mainstream hardware technology for the development of ubiquitous information technology so far. In the era of ‘ big data’ and ‘Internet of Things’ nowadays\, the traditional comput ing architecture based on CMOS hardware has become increasingly inefficien t to support Artificial Intelligence (AI) and Machine Learning (ML)\, whic h necessitates some emerging technologies\, such as memristive technology. Memristive devices(1) have become a promising candidate to enable bio-ins pired computing with much improved efficiency and throughput(2\,3). Such c omputing can be implemented on a Resistive Neural Network(4) with memristi ve synapses(5) and neurons(6) or a Capacitive Neural Network(7\,8) with me mcapacitive synapses and neurons. I will first briefly introduce the promi ses and challenges of memristive materials and devices for those applicati ons and then discuss examples with different levels of bio-inspiration: fi rst\, deep learning accelerators(9) with supervised online learning(10)\; second\, neuromorphic computing for pattern classification with unsupervis ed learning(6)\; last\, other computing applications\, such as reinforceme nt learning(11) for decision making\, artificial nociceptors for robotics( 12)\, provable key destruction(13) and true random number generators(14) f or cybersecurity.\n\n1 Nature Nanotechnology 8\, 13 (2013)\n\n2 Nature mat erials 18\, 309 (2019)\n\n3 Nature Reviews Materials 5\, 173 (2020)\n\n4 N ature Machine Intelligence 1\, 434 (2019)\n\n5 Nature Materials 16\, 101 ( 2017)\n\n6 Nature Electronics 1\, 137 (2018)\n\n7 Nature Communications 9\ , 3208 (2018)\n\n8 Nature Machine Intelligence 1\, 49 (2019)\n\n9 Nature E lectronics 1\, 52 (2018)\n\n10 Nature communications 9\, 2385 (2018)\n\n11 Nature Electronics 2\, 115 (2019)\n\n12 Nature communications 9\, 417 (20 18)\n\n13 Nature Electronics 1\, 548 (2018)\n\n14 Nature communications 8\ , 882 (2017)\n\nEvanston\, Illinois\, United States\, Virtual: https://eve nts.vtools.ieee.org/m/293062 LOCATION:Evanston\, Illinois\, United States\, Virtual: https://events.vtoo ls.ieee.org/m/293062 ORGANIZER:pedram@northwestern.edu SEQUENCE:3 SUMMARY:Memristive Devices for Neuromorphic Computing URL;VALUE=URI:https://events.vtools.ieee.org/m/293062 X-ALT-DESC:Description: <br /><p><em>Northwestern ECE Distinguished Seminar Series</em></p>\n<p><em>Detailed Information: https://www.mccormick.north western.edu/electrical-computer/news-events/events/&nbsp\;</em></p>\n<p><s trong>Professor J. Joshua Yang\, University of Southern California</strong ></p>\n<p>CMOS technology has been the mainstream hardware technology for the development of ubiquitous information technology so far. In the era of &lsquo\;big data&rsquo\; and &lsquo\;Internet of Things&rsquo\; nowadays\ , the traditional computing architecture based on CMOS hardware has become increasingly inefficient to support Artificial Intelligence (AI) and Mach ine Learning (ML)\, which necessitates some emerging technologies\, such a s memristive technology. Memristive devices(1) have become a promising can didate to enable bio-inspired computing with much improved efficiency and throughput(2\,3). Such computing can be implemented on a Resistive Neural Network(4) with memristive synapses(5) and neurons(6) or a Capacitive Neur al Network(7\,8) with memcapacitive synapses and neurons. I will first bri efly introduce the promises and challenges of memristive materials and dev ices for those applications and then discuss examples with different level s of bio-inspiration: first\, deep learning accelerators(9) with supervise d online learning(10)\; second\, neuromorphic computing for pattern classi fication with unsupervised learning(6)\; last\, other computing applicatio ns\, such as reinforcement learning(11) for decision making\, artificial n ociceptors for robotics(12)\, provable key destruction(13) and true random number generators(14) for cybersecurity.</p>\n<p>1 Nature Nanotechnology 8\, 13 (2013)</p>\n<p>2 Nature materials 18\, 309 (2019)</p>\n<p>3 Nature Reviews Materials 5\, 173 (2020)</p>\n<p>4 Nature Machine Intelligence 1\, 434 (2019)</p>\n<p>5 Nature Materials 16\, 101 (2017)</p>\n<p>6 Nature El ectronics 1\, 137 (2018)</p>\n<p>7 Nature Communications 9\, 3208 (2018)</ p>\n<p>8 Nature Machine Intelligence 1\, 49 (2019)</p>\n<p>9 Nature Electr onics 1\, 52 (2018)</p>\n<p>10 Nature communications 9\, 2385 (2018)</p>\n <p>11 Nature Electronics 2\, 115 (2019)</p>\n<p>12 Nature communications 9 \, 417 (2018)</p>\n<p>13 Nature Electronics 1\, 548 (2018)</p>\n<p>14 Natu re communications 8\, 882 (2017)</p>\n<p>&nbsp\;</p> END:VEVENT END:VCALENDAR