Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Hyunsei | - |
dc.contributor.author | Kim, Jiseung | - |
dc.contributor.author | Chen, Hanning | - |
dc.contributor.author | Zeira, Ariela | - |
dc.contributor.author | Srinivasa, Narayan | - |
dc.contributor.author | Imani, Mohsen | - |
dc.contributor.author | Kim, Yeseong | - |
dc.date.accessioned | 2024-02-08T20:10:12Z | - |
dc.date.available | 2024-02-08T20:10:12Z | - |
dc.date.created | 2023-11-10 | - |
dc.date.issued | 2023-07-13 | - |
dc.identifier.isbn | 9798350323481 | - |
dc.identifier.issn | 0738-100X | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/47899 | - |
dc.description.abstract | HD computing is a symbolic representation system which performs various learning tasks in a highly-parallelizable and binary-centric way by drawing inspiration from concepts in human long-term memory. However, the current HD computing is ineffective in extracting high-level feature information for image data. In this paper, we present a neuro-symbolic approach called NSHD, which integrates CNNs and Hyperdimensional (HD) learning techniques to provide efficient learning with state-of-the-art quality. We devise the HD training procedure, which fully integrates knowledge from the deep learning model through a distillation process with optimized computation costs due to the integration. Our experimental results show that NSHD provides high energy efficiency as compared to CNN, e.g., up to 64% with comparable accuracy, and can outperform the learning quality when more computing resources are allowed. We also show the symbolic nature of the NSHD can make the learning humnan-interpretable by exploiting the property of HD computing. © 2023 IEEE. | - |
dc.language | English | - |
dc.publisher | ACM Special Interest Group on Design Automation (SIGDA), IEEE Council on Electronic Design Automation (CEDA) | - |
dc.title | Comprehensive Integration of Hyperdimensional Computing with Deep Learning towards Neuro-Symbolic AI | - |
dc.type | Conference Paper | - |
dc.identifier.doi | 10.1109/DAC56929.2023.10248004 | - |
dc.identifier.scopusid | 2-s2.0-85173103642 | - |
dc.identifier.bibliographicCitation | Design Automation Conference, pp.23709098 | - |
dc.identifier.url | https://60dac.conference-program.com/presentation/?id=RESEARCH523&sess=sess124 | - |
dc.citation.conferencePlace | US | - |
dc.citation.conferencePlace | San Francisco | - |
dc.citation.startPage | 23709098 | - |
dc.citation.title | Design Automation Conference | - |
There are no files associated with this item.