<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>seminar | SKKU IRIS Lab</title>
    <link>https://iris-lab.skku.edu/tag/seminar/</link>
      <atom:link href="https://iris-lab.skku.edu/tag/seminar/index.xml" rel="self" type="application/rss+xml" />
    <description>seminar</description>
    <generator>Wowchemy (https://wowchemy.com)</generator><language>en-us</language><lastBuildDate>Mon, 15 Jun 2026 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://iris-lab.skku.edu/media/icon_hub30d19cd1ec39a1dd8652017ce0a280f_82173_512x512_fill_lanczos_center_3.png</url>
      <title>seminar</title>
      <link>https://iris-lab.skku.edu/tag/seminar/</link>
    </image>
    
    <item>
      <title>Prof. Younghyun Kim’s Seminar on ‘Time-Accuracy Scalable Compute for Energy-Efficient Machine Learning&#39;</title>
      <link>https://iris-lab.skku.edu/post/seminar_younghyun_kim-copy/</link>
      <pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://iris-lab.skku.edu/post/seminar_younghyun_kim-copy/</guid>
      <description>&lt;p&gt;우리 연구실은 2026년 6월 15일, Purdue University 전자전기컴퓨터공학과의 Younghyun Kim 교수님을 모시고 &amp;ldquo;Time-Accuracy Scalable Compute for Energy-Efficient Machine Learning&amp;quot;을 주제로 한 세미나를 개최했습니다.&lt;/p&gt;
&lt;p&gt;Younghyun Kim 교수님은 Purdue University Elmore Family School of Electrical and Computer Engineering의 부교수로, Networked and Embedded Intelligent Systems Lab을 이끌고 계시며 에너지-품질 확장형 컴퓨팅, 엣지/응용/물리 AI, 사이버 물리 시스템 등을 연구하고 계십니다.&lt;/p&gt;
&lt;p&gt;이번 세미나에서는 전통적인 반도체 미세화를 넘어 에너지 효율적인 머신러닝을 실현하기 위한 방법론으로 시간-정확도 확장형 컴퓨팅(time-accuracy scalable computing)이 소개되었습니다. 근사 컴퓨팅(approximate computing)을 통해 정확도를 성능 및 에너지 효율과 맞교환함으로써, 동적 정확도 제어와 전 시스템 최적화가 머신러닝의 정확도를 유지하면서도 지연시간, 전력, 에너지를 크게 절감할 수 있음을 보여주었습니다.&lt;/p&gt;
&lt;p&gt;귀중한 강연으로 깊은 통찰을 나누어 주신 Younghyun Kim 교수님께 진심으로 감사드립니다.&lt;/p&gt;
&lt;p&gt;On June 15, 2026, our lab hosted a seminar featuring Professor Younghyun Kim from the School of Electrical and Computer Engineering at Purdue University, on the topic of &amp;ldquo;Time-Accuracy Scalable Compute for Energy-Efficient Machine Learning.&amp;rdquo;
Younghyun Kim is an Associate Professor in the Elmore Family School of Electrical and Computer Engineering at Purdue University, where he leads the Networked and Embedded Intelligent Systems Lab. His research interests include energy-quality scalable computing, edge/applied/physical AI, cyber-physical systems, and security and privacy for embedded computing systems.
In this seminar, Professor Younghyun Kim presented time-accuracy scalable computing as a path toward energy-efficient machine learning beyond traditional semiconductor scaling. He showed how approximate computing trades accuracy for improved performance and energy efficiency, demonstrating that dynamic accuracy control and full-system optimization can substantially reduce latency, power, and energy while maintaining acceptable machine-learning accuracy.
We sincerely thank Professor Younghyun Kim for sharing his valuable insights through this enlightening lecture.&lt;/p&gt;
</description>
    </item>
    
    <item>
      <title>East Coast Lab Visits and Talks: Resource-Efficient AI via SW-HW Co-design</title>
      <link>https://iris-lab.skku.edu/post/us/</link>
      <pubDate>Mon, 29 Sep 2025 00:00:00 +0000</pubDate>
      <guid>https://iris-lab.skku.edu/post/us/</guid>
      <description>&lt;p&gt;우리 연구실은 2025년 8월 미국 동부의 주요 기관인 Duke University, Cornell Tech, University of Illinois Chicago, University of North Carolina를 방문해 초청 강연과 연구 교류를 진행했습니다.&lt;/p&gt;
&lt;p&gt;강연 주제는 ‘SW–HW 공동 설계를 통한 자원 효율적 인공지능 구현(Enabling Resource-Efficient AI via SW–HW Co-design)’이며, 혼합·다중 정밀도 양자화를 비롯한 압축 기법이 인-메모리 컴퓨팅 등 신흥 하드웨어 패러다임과 어떻게 공동 최적화될 수 있는지를 다뤘습니다. 이를 통해 연산·메모리·전력 제약이 있는 환경에서도 실용적으로 배치 가능한 AI 경로를 제안했습니다.&lt;/p&gt;
&lt;p&gt;강연 전체 영상은 Duke Athena Seminar Series에서 확인하실 수 있습니다.
전체 녹화본: &lt;a href=&#34;https://www.youtube.com/watch?v=_Krud-njeog&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;https://www.youtube.com/watch?v=_Krud-njeog&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;이번 방문을 따뜻하게 맞아 주신 Yiran Chen 교수님, 서재선 교수님, Amit Trivedi 교수님, Roni Sengupta 교수님께 깊이 감사드립니다. 또한 전 일정을 매끄럽게 조율해 주신 전강은 박사님과 준비·운영을 도와준 우리 연구실의 이존이, 이주찬, 연상흠 학생들에게 고마움을 전합니다.&lt;/p&gt;
&lt;p&gt;In August 2025, our lab visited major institutions on the U.S. East Coast—Duke University, Cornell Tech, the University of Illinois Chicago, and the University of North Carolina—to deliver invited talks and conduct research exchanges.&lt;/p&gt;
&lt;p&gt;The talks were on “Enabling Resource-Efficient AI via SW–HW Co-design,” addressing how compression techniques—including mixed- and multi-precision quantization—can be co-optimized with emerging hardware paradigms such as in-memory computing. Through this, we proposed AI deployment pathways that are practically feasible even under compute, memory, and power constraints.&lt;/p&gt;
&lt;p&gt;The full talk video is available from the Duke Athena Seminar Series.
Full recording: &lt;a href=&#34;https://www.youtube.com/watch?v=_Krud-njeog&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;https://www.youtube.com/watch?v=_Krud-njeog&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;We thank Prof. Yiran Chen, Prof. Jae-sun Seo, Prof. Amit Trivedi, and Prof. Roni Sengupta for their warm hospitality; Dr. Kang Eun JEON for seamlessly coordinating every detail; and our students Johnny Rhe, Joo Chan Lee, and Sang Heum Yeon for their tremendous support.&lt;/p&gt;
</description>
    </item>
    
    <item>
      <title>Prof. Yani Ioannou’s Seminar on ‘Training Structured Sparse Neural Networks’</title>
      <link>https://iris-lab.skku.edu/post/seminar_yani/</link>
      <pubDate>Wed, 10 Sep 2025 00:00:00 +0000</pubDate>
      <guid>https://iris-lab.skku.edu/post/seminar_yani/</guid>
      <description>&lt;p&gt;2025년 9월 10일, University of Calgary의 yani 교수님이 성균관대학교를 방문해 “Training Structured Sparse Neural Networks”라는 주제로 세미나를 진행해 주셨습니다. 세미나는 반도체관 400112호에서 열렸고, IRIS 연구실의 고종환 교수님이 호스트를 맡았습니다.&lt;/p&gt;
&lt;p&gt;발표에서는 동적 희소 학습(DST)의 개념과 한계를 정리한 뒤, 학습 단계에서부터 N:M 형태와 같은 하드웨어 친화적 구조적 희소성을 확보하는 Structured RigL(SRigL) 접근을 소개했습니다. 특히 뉴런 어블레이션을 명시적으로 통합해 매우 높은 희소화 수준에서도 일반화 성능을 유지하고, 실제 CPU/GPU 환경에서 추론 속도 향상을 확인한 점이 인상적이었습니다. 이번 세미나를 통해 구조적 희소 신경망 훈련의 배경과 설계상의 고려 요소를 한층 깊이 이해할 수 있었습니다.&lt;/p&gt;
&lt;p&gt;간단한 약력으로, yani 교수님은 University of Calgary Schulich School of Engineering의 전기·소프트웨어공학과에서 재직 중이며 Schulich Research Chair로서 Calgary Machine Learning Lab을 이끌고 있습니다. 이전에는 Vector Institute와 University of Guelph에서 박사후연구원을 지냈고, Google Brain Toronto에서 연구를 수행했습니다. 박사학위는 University of Cambridge에서 취득했으며, 효율적이고 신뢰할 수 있는 딥러닝, 특히 희소 신경망의 학습과 추론에 집중하고 있습니다.&lt;/p&gt;
&lt;p&gt;바쁜 일정에도 귀한 시간을 내어주신 Yani 교수님께 깊이 감사드립니다.&lt;/p&gt;
&lt;p&gt;On September 10, 2025, Prof. Yani Ioannou from the University of Calgary visited Sungkyunkwan University and delivered a seminar titled “Training Structured Sparse Neural Networks.” The talk was held in the Semiconductor Building, Room 400112, and hosted by Prof. Jong Hwan Ko from the IRIS Lab.&lt;/p&gt;
&lt;p&gt;The seminar first reviewed the ideas and practical limitations behind Dynamic Sparse Training (DST), then introduced Structured RigL (SRigL), which learns hardware-friendly N:M structured sparsity during training. A notable point was the explicit use of neuron ablation, enabling strong generalization even at extreme sparsity while demonstrating measurable inference speedups on CPUs and GPUs. The session offered a clear, in-depth view of how to design and train structured sparse neural networks that are both accurate and efficient.&lt;/p&gt;
&lt;p&gt;By way of a short bio, Prof. Ioannou is an Assistant Professor and a Schulich Research Chair in the Schulich School of Engineering at the University of Calgary, where he leads the Calgary Machine Learning Lab. He previously worked as a Postdoctoral Fellow at the Vector Institute and the University of Guelph and conducted research at Google Brain Toronto. He earned his Ph.D. from the University of Cambridge, and his research focuses on efficient and trustworthy deep learning, with an emphasis on training and inference for sparse neural networks.&lt;/p&gt;
&lt;p&gt;We sincerely thank Prof. Yani Ioannou for sharing his time and insights.&lt;/p&gt;
</description>
    </item>
    
    <item>
      <title>Prof. Bokyung Kim’s Seminar on ‘DPIMA: A DRAM-Based Processing-in-Memory Accelerator for Privacy-Preserving Machine Learning&#39;</title>
      <link>https://iris-lab.skku.edu/post/seminar_bokyung_kim/</link>
      <pubDate>Tue, 02 Sep 2025 00:00:00 +0000</pubDate>
      <guid>https://iris-lab.skku.edu/post/seminar_bokyung_kim/</guid>
      <description>&lt;p&gt;2025년 9월 2일, Rutgers University의 김보경 교수님이 성균관대학교를 방문해 “DPIMA: A DRAM-Based Processing-in-Memory Accelerator for Privacy-Preserving Machine Learning”이라는 주제로 세미나를 진행해 주셨습니다. 세미나는 반도체관 400321호에서 열렸고, IRIS 연구실의 고종환 교수님이 호스트를 맡았습니다.&lt;/p&gt;
&lt;p&gt;이번 발표는 ISLPED 2025에서 Best Paper로 선정된 해당 논문을 소개해 주신 자리였습니다. 교수님께서는 프라이버시 보존형 머신러닝을 보다 효율적으로 지원하기 위한 처리-인-메모리(PIM) 관점의 접근을 설명하시며, DRAM의 병렬성을 활용해 데이터 이동을 줄이고 학습 과정에 맞춘 효율적 데이터 흐름을 적용하는 큰 그림을 공유해 주셨습니다. 연구의 의의와 실제 적용 가능성에 대한 논의도 이어져, 프라이버시 보존형 학습을 위한 하드웨어·시스템적 관점에 대해 한층 깊이 있는 이해가 가능했습니다.&lt;/p&gt;
&lt;p&gt;간단한 약력으로, 김보경 교수님은 Rutgers University 전기·컴퓨터공학과에서 재직 중이며, 메모리 중심 가속기와 PIM, 혼성신호 VLSI, 신뢰할 수 있고 효율적인 머신러닝용 칩·아키텍처·시스템을 연구하고 있습니다. 박사학위는 Duke University에서 취득했습니다.&lt;/p&gt;
&lt;p&gt;바쁜 일정에도 귀한 시간을 내어 주신 김보경 교수님께 깊이 감사드립니다.&lt;/p&gt;
&lt;p&gt;On September 2, 2025, Prof. Bokyung Kim from Rutgers University visited Sungkyunkwan University and delivered a seminar titled “DPIMA: A DRAM-Based Processing-in-Memory Accelerator for Privacy-Preserving Machine Learning.” The seminar took place in the Semiconductor Building, Room 400321, and was hosted by Prof. Jong Hwan Ko for the IRIS Lab.&lt;/p&gt;
&lt;p&gt;This talk introduced the paper that was selected as the ISLPED 2025 Best Paper. Prof. Kim outlined a processing-in-memory perspective for enabling privacy-preserving machine learning more efficiently, describing how leveraging DRAM-level parallelism can reduce data movement and how training-phase–aware dataflows can be applied in practice. The discussion highlighted the significance of the work and its potential for real-world deployment, offering the audience a deeper understanding of hardware and system approaches to privacy-preserving training.&lt;/p&gt;
&lt;p&gt;By way of a brief bio, Prof. Kim is a faculty member in Electrical and Computer Engineering at Rutgers University. Her research spans memory-centric accelerators and PIM, mixed-signal VLSI, and trustworthy, efficient machine-learning chips, architectures, and systems. She received her Ph.D. from Duke University.&lt;/p&gt;
&lt;p&gt;We sincerely thank Prof. Bokyung Kim for sharing her time and insights with the IRIS Lab.&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
