[인공지능시스템반도체연구센터 기업가정신교육] 1. 일시: 2024.09.12(목) 14:30 ~ 18:002. 장소: 서강대학교 정하상관 309호   

    🔹연사 : 삼성전자 혁신센터, 정재훈 그룹장   🔹내용 : 반도체 산업의 특징 및 반도체의 종류와 기능에 대해 간략히 기술하고        제품 개발 및 양산 프로세스와 반도체 주요 8대 공정의 간략한 소개를 통해         현재 반도체 제품의 주요 이슈의 이해를 도모함.        문제 해결 기법으로 제조 데이터와 시뮬레이션 기반의 3차원 구조 계측 및         특성과 불량 예측 솔루션을 통한 Digital Twin 기술을 설명함.        반도체 산업에서 개발 혁신 사례를 공유하고 향후 Digital Twin 기술이 나아가야 할 방향에 대해 고찰        하고자 함.    🔹일정 및 장소 : 8/30일(금) 16:00, 정하상관 311호  🔹주관 : 강석주 교수 연구실    

- 일시: 2024년 8월 9일(금) 오후 4시- 장소: 김대건관 K302호- 주제: Design of computing-in-memory: analog vs. digital- 연사: 김태형 교수님 (Nanyang Technological University - NTU Singapore)- 주관: 범진욱 교수 연구실

 1. 강사 : 김회준 전무 (NVIDIA Korea))   2. 일시 및 장소 : 8/1(목) 16:00 ~ 17:00, J311   3. 제목 : 엔비디아 소개 및 GPU 제품 활용 사례  4. 개요 : 엔비디아는 최근 인공지능 기술에서 빼 놓을 수 없는 회사로 1993년 젠슨황에 의해 창업 되었으며 혁신적인 GPU 개발을 통해 게임, 전문 디자인, 데이타센터, 인공지능, 자율주행 등에서 주요한 발전을 이루고 있습니다.  이번 발표는 엔비디아 회사 소개, 주력 제품 및 로드맵, 데이터센터 비즈니스 현황 및 조직문화 등을 소개 드릴 예정입니다.   5. 주관: 강석주 교수 연구실 

 🔹연사: 석민구 교수  🔹일시: 2024년 8월 13일 오후 4시 🔹장소: 정하상관 311호  🔹Title: Recent Advance in Digital In-Memory-Computing Processors 🔹Abstract: In the last decade, SRAM-based in-memory computing (IMC) hardware has received significant research attention for its massive energy efficiency and performance boost. Recently, in the IMC research, we are observing a rapidly growing interest in the digital-oriented implementation of the IMC hardware. In light of this, by focusing on digital IMC hardware, we will first introduce two notable macro-level developments, namely D6CIM which adopts hardware-reusu architecture and STAR-SRAM which supports floating-point arithmetic. Then, we will introduce two notable digital IMC-based processors for convolutional neural network workloads, namely iMCU and an first 1-TFLOP/W accelerator. Those processors successfully leverage the IMC techniques for largely boosting efficiency while also addressing the overhead of off-chip data traffic, which otherwise would become dominating overall efficiency. 🔹Bio: Mingoo Seok is an associate professor of Electrical Engineering at Columbia University. He received his B.S. from Seoul National University, South Korea, in 2005, and his M.S. and Ph.D. degree from the University of Michigan in 2007 and 2011, respectively, all in electrical engineering. His research interests are various aspects of VLSI circuits and architecture, including ultra-low-power integrated systems, cognitive and machine-learning computing, an adaptive technique for the process, voltage, temperature variations, transistor wear-out, integrated power management circuits, event-driven controls, and hybrid continuous and discrete computing. He won the 2015 NSF CAREER award and the 2019 Qualcomm Faculty Award. He is the technical program committee member for multiple conferences, including IEEE International Solid-State Circuits Conference (ISSCC). In addition, He has been an IEEE SSCS Distinguished Lecturer for Feb/2023-Feb/2025 and an associate editor for IEEE Transactions on Circuits and Systems Part I (TCAS-I) (2014-2016), IEEE Transactions on VLSI Systems (TVLSI) (2015-present), IEEE Solid-State Circuits Letter (SSCL) (2017-2022), and as a guest associate editor for IEEE Journal of Solid-State Circuits (JSSC) (2019).  🔹주관: 강석주 교수 연구실    

 1. 강사 : 윤성희 박사 (Erudio Bio, Inc./ VP - AI Technology & Product Strategy) 2. 일시 및 장소 : 6/24(월) 15:00, J311 3. 제목 : LLM & genAI - Technology, Business Application, Market Outlook, and Important Questions 4. AbstractThe contemporary landscape of artificial intelligence (AI) has undergone a profound transformation, driven by the emergence and widespread application of large language models (LLMs), with OpenAI's ChatGPT based on GPT-x models serving as a pivotal catalyst. This seminar, tailored for university faculty and students, delves into the dynamic intersection of LLMs and generative AI (genAI), engaging both major industry players and agile startups in a comprehensive exploration.The first part of the seminar initiates with a concise overview of LLMs, followed by a nuanced technical analysis focusing on the attention mechanism, a linchpin within the Transformer architecture. This examination aims to unveil the intricacies underlying the training and inference processes of LLMs having Transformer components, offering valuable insights into their remarkable capabilities.Expanding the discourse to genAI, encompassing both technical and business dimensions, the seminar illustrates how LLMs and genAI collectively herald a new era. Numerous examples showcase how these technologies stimulate the creation of innovative applications and transformative business models. The first part of the seminar culminates with an exploration of current trends in genAI, providing strategic insights to navigate market dynamics and foster the development of impactful products.The second half of the seminar shifts focus to critical non-technical topics surrounding the rapid progress of AI development. Engaging in meaningful discussions, we explore the rationale behind pursuing human-level AI, potential biases, ethical and legal challenges, and the elusive concept of AI consciousness. The speaker encourages active participation from the audience, fostering debates on these intriguing topics. The seminar concludes with the speaker's contemplation on the knowledge, reasoning, and belief systems of AI, particularly those inherent to LLMs, offering a thought-provoking finale to this exploration of the frontiers of AI.  5. 주관: 강석주 교수 연구실 

 - 주제: AI-Accelerated HW/SW Systems in the Era of Large Language Models and On-Device AI- 연사: KAIST 박종세 교수- 일시: 5월 27일(월) 오후 4시- 장소: K304- 개요 The advent of Generative AI (GenAI), represented by Large Language Models (LLMs), is rapidly changing the way that our society works. IT industry is in the process of actively deploying GenAI for real-world applications. However, GenAI inferencing requires a massive amount of computing and memory resources, necessitating the use of a cloud-based inferencing serving system to amortize the operation cost. Therefore, there is an urgent need to develop an efficient, cost-effective, and scalable LLM inference serving system for unlocking the limitless potential of such remarkable algorithmic advances. Rather disjointly, IT industry is transitioning its attention towards on-device systems, including autonomous systems (e.g., vehicles and robots) and AR/VR devices. Building efficient on-device AI systems poses a different set of requirements and constraints than cloud-based systems, calling for aggressive research efforts in the domain. To this end, I will introduce two research projects: (1) NeuPIMs: a Processing-in-Memory (PIM) based acceleration for LLM inferencing, and (2) DaCapo: an on-device continuous learning acceleration for autonomous systems. Both works aim to build a hardware-software co-designed acceleration solutions, which will be deeply discussed in this talk.  - 주관: 강석주 교수 연구실  

 - 주제: The World’s Smallest Active Electronic System & Its Applications- 연사: Inhee Lee (University of Pittsburgh): Inhee Lee earned his B.S. and M.S. in electrical and electronic engineering from Yonsei University in 2006 and 2008, respectively. He obtained his Ph.D. in electrical and electronic engineering from the University of Michigan in 2014. From 2015 to 2019, he served as an assistant research scientist at the University of Michigan. In 2019, he became an assistant professor at the University of Pittsburgh. His research focuses on developing millimeter-scale or smaller sensing/computing systems for ecological, biomedical, and AI-of-things applications. Dr. Lee is currently serving as a Technical Program Committee (TPC) Member for IEEE VLSI Symposium, CICC, A-SSCC, CAS Analog Signal Processing, and ISLPED.- 일시: 5 월 7일 (화) 오후 4시- 장소: K203호- 개요 : Miniature Internet-of-Things (IoT) systems have unique feature sets that include wireless communication, energy harvesting, and a small form factor, thus enabling non-invasive, secure placement for biomedical, ecological, surveillance, and infrastructure applications, among others. There has been substantial research on the miniaturization of IoT systems. The size of the bare die is often only 1-2 mm; however, the associated systems are typically much larger than just the die, resulting in centimeter-size systems due to included peripherals such as batteries and casings. This leads to a design challenge for the electronics of miniaturized systems because the maximum physical battery size and battery storage capacity are severely limited. In this talk, I will discuss the challenges in developing miniature IoT systems and introduce a millimeter-scale system platform. The system has been developed as the world’s smallest active electronic system. To optimize circuit performance, the system is constructed from die fabricated in different technologies which are then stacked and wire-bonded together. The stacked structure increases silicon area per unit volume and makes it easy to swap layers in and out for flexibility in system configuration. Additionally, I will highlight two intriguing use scenarios of miniature systems for ecological studies. 🔹주관: 홍성완 교수 연구실   

- 주제: 제조 지능화를 위한 인공지능 기술 (결함검사, 설비상태진단 등 사례 중심)- 연사: 윤종필 박사 (한국생산기술연구원)- 일시: 3월 19일(화) 오후 16시 - 장소: AS 510호- 개요 : 포스크 코로나 시대 제조 분야의 디지털 전환 가속화가 부각되고 있고, 세계 주요국은 성장 한계인 제조업을, AI융합을 통해 신성장동력으로 육성하고 있음. 이번 세미나에서는 제조업 지능화를 위해 연구되고 있는 인공지능 기술을 사례 위주로 강연 예정임.  - 주관: 강석주 교수 연구실       

 

🔹주제: Next G Alliance Overview and Research Priorities on 6G Technologies🔹날짜: 2월 8일(목) 오전 10시 ~ 11시 🔹연사: 전정호 박사 (Director, Standards and Mobility Innovation Lab. Samsung Research America)🔹참가 Zoom 회의 - https://sogang-ac-kr.zoom.us/j/83881604735 - 회의 ID: 838 8160 4735🔹주관: 강석주 교수 연구실