BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Denver BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0700 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:MDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0600 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:MST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20241028T153437Z UID:301FBCA6-AE75-4B33-AB91-B454B64BB4AA DTSTART;TZID=America/Denver:20241018T110000 DTEND;TZID=America/Denver:20241018T120000 DESCRIPTION:The slowing down of Moore’s Law growth has coincided with esc alating computational demands from machine learning and artificial intelli gence. An emerging trend in computing involves building physics-inspired c omputers that leverage the intrinsic properties of physical systems for sp ecific domains of applications. Probabilistic computing with probabilistic bits (p-bits) has emerged as a promising candidate in this area\, offerin g an energy-efficient approach to probabilistic algorithms and application s [1]-[4].\n\nSeveral implementations of p-bits\, ranging from standard co mplementary metal oxide semiconductor (CMOS) technology to nanodevices\, h ave been demonstrated. Among these\, the most promising p-bits appear to b e based on stochastic magnetic tunnel junctions (sMTJs) [2]. Such sMTJs ha rness the natural randomness in low-barrier nanomagnets to create energy-e fficient and fast fluctuations\, up to gigahertz frequencies [4]. In this talk\, I will discuss how magnetic p-bits can be combined with conventiona l CMOS to create hybrid probabilistic-classical computers for various appl ications. I will provide recent examples of how p-bits are naturally appli cable to combinatorial optimization\, such as solving the Boolean satisfia bility problem [3]\, energy-based generative machine learning models like deep Boltzmann machines\, and quantum simulation for investigating many-bo dy quantum systems. Through experimentally informed projections for scaled p-bit computers using sMTJs\, I will demonstrate how physics-inspired pro babilistic computing can lead to graphics-processing-unit-like success sto ries for a sustainable future in computing.\n\n[1] S. Chowdhury\, A. Grima ldi\, N. A. Aadit\, S. Niazi\, M. Mohseni\, S. Kanai\, H. Ohno\, S. Fukami \, L. Theogarajan\, G. Finocchio\, S. Datta\, K. Y. Camsari\, “A Full-St ack View of Probabilistic Computing with p-Bits: Devices\, Architectures a nd Algorithms\,” IEEE J. Expl. Solid-State Comp. Dev. Cir. 9\, 1-11 (202 3).\n\n[2] W. A. Borders\, A. Z. Pervaiz\, S. Fukami\, K. Y. Camsari\, H. Ohno\, S. Datta\, “Integer Factorization Using Stochastic Magnetic Tunne l Junctions\,” Nature 573\, 390-393 (2019).\n\n[3] N. A. Aadit\, A. Grim aldi\, M. Carpentieri\, L. Theogarajan\, J. M. Martinis\, G. Finocchio\, K . Y. Camsari\, “Massively Parallel Probabilistic Computing with Sparse I sing Machines\,” Nature Electronics 5\, 460–468 (2022).\n\n[4] N. S. S ingh\, S. Niazi\, S. Chowdhury\, K. Selcuk\, H. Kaneko\, K. Kobayashi\, S. Kanai\, H. Ohno\, S. Fukami\, K. Y. Camsari\, “Hardware Demonstration o f Feedforward Stochastic Neural Networks with Fast MTJ-Based p-Bits\,” I EEE Int. Electron Dev. Meeting (2023).\n\nCo-sponsored by: UCCS\n\nSpeaker (s): Kerem Camsari\n\nRoom: A204\, Bldg: Osborne Center for Science and En gineering\, 1420 Austin Bluffs Pkwy\, Colorado Springs\, Colorado\, United States\, 80918\, Virtual: https://events.vtools.ieee.org/m/442795 LOCATION:Room: A204\, Bldg: Osborne Center for Science and Engineering\, 14 20 Austin Bluffs Pkwy\, Colorado Springs\, Colorado\, United States\, 8091 8\, Virtual: https://events.vtools.ieee.org/m/442795 ORGANIZER:eiacocca@uccs.edu SEQUENCE:9 SUMMARY:Probabilistic Computing With p-Bits: Optimization\, Machine Learnin g and Quantum Simulation URL;VALUE=URI:https://events.vtools.ieee.org/m/442795 X-ALT-DESC:Description: <br /><p class="MsoNormal" style="text-align: justi fy\;"><!-- [if gte vml 1]><v:shapetype\n id="_x0000_t75" coordsize="21600\ ,21600" o:spt="75" o:preferrelative="t"\n path="m@4@5l@4@11@9@11@9@5xe" fi lled="f" stroked="f">\n <v:stroke joinstyle="miter"/>\n <v:formulas>\n <v :f eqn="if lineDrawn pixelLineWidth 0"/>\n <v:f eqn="sum @0 1 0"/>\n <v: f eqn="sum 0 0 @1"/>\n <v:f eqn="prod @2 1 2"/>\n <v:f eqn="prod @3 2160 0 pixelWidth"/>\n <v:f eqn="prod @3 21600 pixelHeight"/>\n <v:f eqn="sum @0 0 1"/>\n <v:f eqn="prod @6 1 2"/>\n <v:f eqn="prod @7 21600 pixelWid th"/>\n <v:f eqn="sum @8 21600 0"/>\n <v:f eqn="prod @7 21600 pixelHeigh t"/>\n <v:f eqn="sum @10 21600 0"/>\n </v:formulas>\n <v:path o:extrusion ok="f" gradientshapeok="t" o:connecttype="rect"/>\n <o:lock v:ext="edit" a spectratio="t"/>\n</v:shapetype><v:shape id="Picture_x0020_1" o:spid="_x00 00_s1026" type="#_x0000_t75"\n style='position:absolute\;left:0\;text-alig n:left\;margin-left:0\;margin-top:.65pt\;\n width:121.4pt\;height:121.4pt\ ;z-index:2\;visibility:visible\;mso-wrap-style:square\;\n mso-height-perce nt:0\;mso-wrap-distance-left:9pt\;mso-wrap-distance-top:0\;\n mso-wrap-dis tance-right:9pt\;mso-wrap-distance-bottom:0\;\n mso-position-horizontal:le ft\;mso-position-horizontal-relative:margin\;\n mso-position-vertical:abso lute\;mso-position-vertical-relative:text\;\n mso-height-percent:0\;mso-he ight-relative:margin'>\n <v:imagedata src="file:///C:/Users/EZIOLA~1/AppDa ta/Local/Temp/msohtmlclip1/01/clip_image001.jpg"\n o:title=""/>\n <w:wrap type="tight" anchorx="margin"/>\n</v:shape><![endif]--><!-- [if !vml]-->< !--[endif]--><span style="font-size: 12.0pt\; line-height: 107%\;">The slo wing down of Moore&rsquo\;s Law growth has coincided with escalating compu tational demands from machine learning and artificial intelligence. An eme rging trend in computing involves building physics-inspired computers that leverage the intrinsic properties of physical systems for specific domain s of applications. Probabilistic computing with probabilistic bits (p-bits ) has emerged as a promising candidate in this area\, offering an energy-e fficient approach to probabilistic algorithms and applications [1]-[4].</s pan></p>\n<p class="MsoNormal" style="text-align: justify\;"><span style=" font-size: 12.0pt\; line-height: 107%\;">Several implementations of p-bits \, ranging from standard complementary metal oxide semiconductor (CMOS) te chnology to nanodevices\, have been demonstrated. Among these\, the most p romising p-bits appear to be based on stochastic magnetic tunnel junctions (sMTJs) [2]. Such sMTJs harness the natural randomness in low-barrier nan omagnets to create energy-efficient and fast fluctuations\, up to gigahert z frequencies [4]. In this talk\, I will discuss how magnetic p-bits can b e combined with conventional CMOS to create hybrid probabilistic-classical computers for various applications. I will provide recent examples of how p-bits are naturally applicable to combinatorial optimization\, such as s olving the Boolean satisfiability problem [3]\, energy-based generative ma chine learning models like deep Boltzmann machines\, and quantum simulatio n for investigating many-body quantum systems. Through experimentally info rmed projections for scaled p-bit computers using sMTJs\, I will demonstra te how physics-inspired probabilistic computing can lead to graphics-proce ssing-unit-like success stories for a sustainable future in computing.</sp an></p>\n<p class="MsoNormal" style="text-align: justify\;"><span style="f ont-size: 12.0pt\; line-height: 107%\;">[1] S. Chowdhury\, A. Grimaldi\, N . A. Aadit\, S. Niazi\, M. Mohseni\, S. Kanai\, H. Ohno\, S. Fukami\, L. T heogarajan\, G. Finocchio\, S. Datta\, K. Y. Camsari\, &ldquo\;A Full-Stac k View of Probabilistic Computing with p-Bits: Devices\, Architectures and Algorithms\,&rdquo\; <em>IEEE J. Expl. Solid-State Comp. Dev. Cir.</em> 9 \, 1-11 (2023).</span></p>\n<p class="MsoNormal" style="text-align: justif y\;"><span style="font-size: 12.0pt\; line-height: 107%\;">[2] W. A. Borde rs\, A. Z. Pervaiz\, S. Fukami\, K. Y. Camsari\, H. Ohno\, S. Datta\, &ldq uo\;Integer Factorization Using Stochastic Magnetic Tunnel Junctions\,&rdq uo\; <em>Nature </em>573\, 390-393 (2019).</span></p>\n<p class="MsoNormal " style="text-align: justify\;"><span style="font-size: 12.0pt\; line-heig ht: 107%\;">[3] N. A. Aadit\, A. Grimaldi\, M. Carpentieri\, L. Theogaraja n\, J. M. Martinis\, G. Finocchio\, K. Y. Camsari\, &ldquo\;Massively Para llel Probabilistic Computing with Sparse Ising Machines\,&rdquo\; <em>Natu re Electronic</em>s 5\, 460&ndash\;468 (2022).</span></p>\n<p class="MsoNo rmal" style="text-align: justify\;"><span style="font-size: 12.0pt\; line- height: 107%\;">[4] N. S. Singh\, S. Niazi\, S. Chowdhury\, K. Selcuk\, H. Kaneko\, K. Kobayashi\, S. Kanai\, H. Ohno\, S. Fukami\, K. Y. Camsari\, &ldquo\;Hardware Demonstration of Feedforward Stochastic Neural Networks w ith Fast MTJ-Based p-Bits\,&rdquo\; <em>IEEE Int. Electron Dev. Meeting</e m> (2023).</span></p> END:VEVENT END:VCALENDAR