BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240801T145918Z UID:B427D2AD-B485-4C3D-8C92-2B78EFE06983 DTSTART;TZID=America/New_York:20240731T193000 DTEND;TZID=America/New_York:20240731T203000 DESCRIPTION:Neuromorphic Computing for Future AI Systems\n\nCory Merkel\, P h.D.\n\nDirector\, Brain Lab\n\nAssistant Professor\, Department of Comput er Engineering\, RIT\n\nAbstract: Artificial intelligence (AI) has become the linchpin in a growing number of products\, services\, and research pro grams which are aimed at automating and enhancing the human decision-makin g process. There is no doubt that AI will play a central role in the futur e of healthcare\, transportation\, manufacturing\, and defense\, among oth ers. However\, the rapidly growing size\, weight\, and power (SWaP) cost o f AI algorithms limits their deployment on devices with practical computin g and energy constraints (satellites\, wearables\, wireless sensors). In t his talk\, I will discuss our lab’s efforts to bridge this gap by closel y emulating the structure and function of biological brains\, with the ult imate goal of enabling AI in the most SWaP-constrained environments. This research takes a holistic approach\, examining the entire AI stack\, from devices and circuits to algorithms and applications. At the lowest level\ , I will present our research on memristor-based circuits for implementing weighted communication pathways in artificial neural networks (ANNs) and spiking neural networks (SNNs). Memristors reduce the power and latency as sociated with running ANNs/SNNs on traditional computer architectures by d irectly emulating both the memory and computation of biological synapses. In addition\, memristor plasticity enables on-chip learning and allows ANN s/SNNs to function in the presence of hardware defects and process variati ons. Moving up the design hierarchy\, the talk will highlight ideas for bi ologically-inspired energy management in neuromorphic systems and efficien t ANN/SNN topologies. Finally\, the talk will provide an overview of our r esearch related to the trustworthiness and potential security vulnerabilit ies of AI hardware with ties to human perception and psychology.\n\nBio: C ory Merkel is an assistant professor with the Department of Computer Engin eering\, Rochester Institute of Technology. He earned his BS and MS degree s in computer engineering (2011) and a Ph.D. in microsystems engineering ( 2015) from RIT. From 2016 to 2018\, Dr. Merkel was a research electronics engineer with the Information Directorate\, Air Force Research Lab. He is currently the director of the Brain Lab\, a multidisciplinary research lab aimed at fundamental research to enable the next generation of ultra-effi cient and trustworthy AI systems. His current research focuses on mapping of AI algorithms\, primarily artificial and spiking neural networks\, to m ixed-signal hardware\, design of brain-inspired computing systems using em erging technologies\, and trustworthy AI hardware. Dr. Merkel’s research has been published in a number of peer-reviewed conferences\, journals\, and books.\n\nCo-sponsored by: IEEE\, Rochester Section\, Region 1\n\nSpea ker(s): \, \, \n\nAgenda: \nWednesday\, July 31st\, 7:30 PM: Introduction of Dr. Cory Merkel\, tonight's speaker.\n\n7:35 PM: Presentation: Neuromor phic Computing for AI Systems\n\n8:20 PM: Questions and Answers\n\n8:30 PM : Webinar end\n\nVirtual: https://events.vtools.ieee.org/m/426383 LOCATION:Virtual: https://events.vtools.ieee.org/m/426383 ORGANIZER:Cory Merkel <cemeec@rit.edu> SEQUENCE:155 SUMMARY:Webinar: Neuromorphic Computing for Future AI Systems URL;VALUE=URI:https://events.vtools.ieee.org/m/426383 X-ALT-DESC:Description: <br /><p class="MsoNormal" style="margin-bottom: 0i n\; text-align: center\;" align="center"><strong style="mso-bidi-font-weig ht: normal\;"><span style="font-size: 16.0pt\; mso-bidi-font-size: 11.0pt\ ; line-height: 115%\;">Neuromorphic Computing for Future AI Systems</span> </strong></p>\n<p class="MsoNormal" style="margin-bottom: 0in\; text-align : center\;" align="center"><strong style="mso-bidi-font-weight: normal\;"> <span style="font-size: 12.0pt\; mso-bidi-font-size: 11.0pt\; line-height: 115%\;">Cory Merkel\, Ph.D.</span></strong></p>\n<p class="MsoNormal" sty le="margin-bottom: 0in\; text-align: center\;" align="center"><strong styl e="mso-bidi-font-weight: normal\;"><span style="font-size: 12.0pt\; mso-bi di-font-size: 11.0pt\; line-height: 115%\;">Director\, Brain Lab</span></s trong></p>\n<p class="MsoNormal" style="margin-bottom: 0in\; text-align: c enter\;" align="center"><strong style="mso-bidi-font-weight: normal\;"><sp an style="font-size: 12.0pt\; mso-bidi-font-size: 11.0pt\; line-height: 11 5%\;">Assistant Professor\, Department of Computer Engineering\, RIT</span ></strong></p>\n<p class="MsoNormal" style="text-align: justify\;"><strong style="mso-bidi-font-weight: normal\;">Abstract:</strong><span style="mso -spacerun: yes\;">&nbsp\; </span>Artificial intelligence (AI) has become t he linchpin in a growing number of products\, services\, and research prog rams which are aimed at automating and enhancing the human decision-making process.<span style="mso-spacerun: yes\;">&nbsp\; </span>There is no doub t that AI will play a central role in the future of healthcare\, transport ation\, manufacturing\, and defense\, among others.<span style="mso-spacer un: yes\;">&nbsp\; </span>However\, the rapidly growing size\, weight\, an d power (SWaP) cost of AI algorithms limits their deployment on devices wi th practical computing and energy constraints (satellites\, wearables\, wi reless sensors).<span style="mso-spacerun: yes\;">&nbsp\; </span>In this t alk\, I will discuss our lab&rsquo\;s efforts to bridge this gap by closel y emulating the structure and function of biological brains\, with the ult imate goal of enabling AI in the most SWaP-constrained environments.<span style="mso-spacerun: yes\;">&nbsp\; </span>This research takes a holistic approach\, examining the entire AI stack\, from devices and circuits to al gorithms and applications. <span style="mso-spacerun: yes\;">&nbsp\;</span >At the lowest level\, I will present our research on memristor-based circ uits for implementing weighted communication pathways in artificial neural networks (ANNs) and spiking neural networks (SNNs).<span style="mso-space run: yes\;">&nbsp\; </span>Memristors reduce the power and latency associa ted with running ANNs/SNNs on traditional computer architectures by direct ly emulating both the memory and computation of biological synapses.<span style="mso-spacerun: yes\;">&nbsp\; </span>In addition\, memristor plastic ity enables on-chip learning and allows ANNs/SNNs to function in the prese nce of hardware defects and process variations.<span style="mso-spacerun: yes\;">&nbsp\; </span>Moving up the design hierarchy\, the talk will highl ight ideas for biologically-inspired energy management in neuromorphic sys tems and efficient ANN/SNN topologies.<span style="mso-spacerun: yes\;">&n bsp\; </span>Finally\, the talk will provide an overview of our research r elated to the trustworthiness and potential security vulnerabilities of AI hardware with ties to human perception and psychology.</p>\n<p class="Mso Normal" style="text-align: justify\;"><strong style="mso-bidi-font-weight: normal\;">Bio:<span style="mso-spacerun: yes\;">&nbsp\; </span></strong>C ory Merkel is an assistant professor with the Department of Computer Engin eering\, Rochester Institute of Technology.<span style="mso-spacerun: yes\ ;">&nbsp\; </span>He earned his BS and MS degrees in computer engineering (2011) and a Ph.D. in microsystems engineering (2015) from RIT.<span style ="mso-spacerun: yes\;">&nbsp\; </span>From 2016 to 2018\, Dr. Merkel was a research electronics engineer with the Information Directorate\, Air Forc e Research Lab.<span style="mso-spacerun: yes\;">&nbsp\; </span>He is curr ently the director of the Brain Lab\, a multidisciplinary research lab aim ed at fundamental research to enable the next generation of ultra-efficien t and trustworthy AI systems.<span style="mso-spacerun: yes\;">&nbsp\; </s pan>His current research focuses on mapping of AI algorithms\, primarily a rtificial and spiking neural networks\, to mixed-signal hardware\, design of brain-inspired computing systems using emerging technologies\, and trus tworthy AI hardware.<span style="mso-spacerun: yes\;">&nbsp\; </span>Dr. M erkel&rsquo\;s research has been published in a number of peer-reviewed co nferences\, journals\, and books. <span style="mso-spacerun: yes\;">&nbsp\ ;</span><span style="mso-spacerun: yes\;">&nbsp\;&nbsp\;</span><span style ="mso-spacerun: yes\;">&nbsp\;</span></p><br /><br />Agenda: <br /><p>Wedn esday\, July 31st\, 7:30 PM:&nbsp\; Introduction of Dr. Cory Merkel\, toni ght's speaker.</p>\n<p>&nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nb sp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp \; &nbsp\; &nbsp\; &nbsp\; &nbsp\;7:35 PM:&nbsp\; Presentation:&nbsp\; Neu romorphic Computing for AI Systems</p>\n<p>&nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; & nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\;8:20 PM:&nbsp\; Ques tions and Answers</p>\n<p>&nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &n bsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\;8:30 PM:&nbsp\; Webinar end</p> END:VEVENT END:VCALENDAR