BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211208T164511Z
LOCATION:3014
DTSTART;TZID=America/Los_Angeles:20211209T133000
DTEND;TZID=America/Los_Angeles:20211209T144000
UID:dac_DAC 2021_sess118@linklings.com
SUMMARY:Let There Be Light: Emerging Technology for Intelligent Systems
DESCRIPTION:Research Manuscript\n\nModern artificial intelligence (AI) met
 hods have high computing and memory costs. This session focuses on the use
  of emerging technologies, from silicon photonics to in-memory computing, 
 to mitigate these costs and move us towards more efficient hardware implem
 entations for AI.\n\nCrossLight: A Cross-Layer Optimized Silicon Photonic 
 Neural Network Accelerator\n\nSunny\n\nDomain-specific neural network acce
 lerators have seen growing interest in recent years due to their improved 
 energy efficiency and inference performance compared to CPUs and GPUs. In 
 this paper, we propose a novel cross-layer optimized neural network accele
 rator called CrossLight that leverages sili...\n\n---------------------\nL
 ow-Cost and Effective Fault-Tolerance Enhancement Techniques for Emerging 
 Memories-Based Deep Neural Networks\n\nNguyen\n\nEmerging non-volatile mem
 ory (NVM) technologies with better scalability, non-volatility, and good r
 ead performance are widely researched, especially for the Deep Neural Netw
 orks (DNNs) applications. However, emerging NVMs face reliability concerns
  due to stuck-at faults, which can severely degrade t...\n\n--------------
 -------\nTowards Resilient Deployment of In-Memory Neural Networks with Hi
 gh Throughput\n\nZhang\n\nResistive computing systems (RCSs) promise exasc
 ale computing capabilities to inference engines for deep learning. In this
  paper, we propose a framework for resilient deployment of high throughput
  CNNs to RCSs.  The framework is based on integrating a data layout organi
 zation step and a distribution...\n\n\nTopic: Design\n\nKeyword: AI/ML Sys
 tem Design\n\nVirtual Program: Presented In-Person
END:VEVENT
END:VCALENDAR