Session

· Contributors · Organizations · Search Program · Flagged · Happening Now

Research Manuscript: AI Paradigms beyond Deep Neural Networks

Session Chairs

DescriptionAs hardware performance slows in the post-Moore era, we need to explore new computing paradigms to improve the energy efficiency of AI. This session delves into cutting-edge algorithm research beyond DNNs and its practical applications. The presentations in this session discuss Optical Neural Networks, Random Forests, Hyper-Dimensional Computing, Approximate Nearest Neighbor Search, and Graph Neural Networks.

Event TypeResearch Manuscript

TimeWednesday, June 2610:30am - 12:00pm PDT

Location3001, 3rd Floor

Topics

Keywords

Presentations

10:30am - 10:45am PDT	Zeroth-Order Optimization of Optical Neural Networks with Linear Combination Natural Gradient and Calibrated Model Authors Hiroshi Sawada Kazuo Aoyama Kohei Ikeda
10:45am - 11:00am PDT	Order-Preserving Cryptography for the Confidential Inference in Random Forests: FPGA Design and Implementation Authors Rupesh Karn Kashif Nawaz Ibrahim (Abe) Elfadel
11:00am - 11:15am PDT	SMORE: Similarity-Based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classification Authors Junyao Wang Mohammad Al Faruque
11:15am - 11:30am PDT	Leanor: A Learning-Based Accelerator for Efficient Approximate Nearest Neighbor Search via Reduced Memory Access Authors Yi Wang Huan Liu Jianan Yuan Jiaxian Chen Tianyu Wang Chenlin Ma Rui Mao
11:30am - 11:45am PDT	GNNavigator: Towards Adaptive Training of Graph Neural Networks via Automatic Guideline Exploration Authors Tong Qiao Jianlei Yang Yingjie Qi Ao Zhou Chen Bai Bei Yu Weisheng Zhao Chunming Hu
11:45am - 12:00pm PDT	Less is More: Hop-Wise Graph Attention for Scalable and Generalizable Learning on Circuits Authors Chenhui Deng Zichao Yue Cunxi Yu Gokce Sarar Ryan Carey Rajeev Jain Zhiru Zhang

DAC 2024