Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Weier Wan"'
Autor:
Weier Wan, Rajkumar Kubendran, Clemens Schaefer, Sukru Burc Eryilmaz, Wenqiang Zhang, Dabin Wu, Stephen Deiss, Priyanka Raina, He Qian, Bin Gao, Siddharth Joshi, Huaqiang Wu, H.-S. Philip Wong, Gert Cauwenberghs
Publikováno v:
Nature, vol 608, iss 7923
Realizing increasingly complex artificial intelligence (AI) functionalities directly on edge devices calls for unprecedented energy efficiency of edge hardware. Compute-in-memory (CIM) based on resistive random-access memory (RRAM)1 promises to meet
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8d1649d2a82ab9118081a798b26b0547
https://doi.org/10.1038/s41586-022-04992-8
https://doi.org/10.1038/s41586-022-04992-8
Autor:
Yue-Der Chih, Weier Wan, Ching-Hua Wang, Harry Chuang, Hongjie Wang, Po-Han Chen, Wei-Chen Chen, Haitong Li, Priyanka Raina, Akash Levy, Win-San Khwa, H.-S. Philip Wong, Meng-Fan Chang
Publikováno v:
IEEE Transactions on Electron Devices. 68:6637-6643
Learning from a few examples (one/few-shot learning) on the fly is a key challenge for on-device machine intelligence. We present the first chip-level demonstration of one-shot learning with Stanford Associative memory for Programmable, Integrated Ed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::28389298af4c7aeebdd594f2770b3e66
https://doi.org/10.1109/ted.2021.3110464
https://doi.org/10.1109/ted.2021.3110464
Autor:
S. Burc Eryilmaz, Matthew J. BrightSky, Jesse Engel, Ryan Zarcone, Weier Wan, Sangbum Kim, Chung H. Lam, Hsiang-Lan Lung, Bruno A. Olshausen, H.-S. Philip Wong
Publikováno v:
Scientific Reports, Vol 10, Iss 1, Pp 1-1 (2020)
An amendment to this paper has been published and can be accessed via a link at the top of the paper.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::306bbd524dc1979eab3057c1770dc01c
https://doi.org/10.1038/s41598-020-70121-y
https://doi.org/10.1038/s41598-020-70121-y
Publikováno v:
ICONS
An ultra-low power integrate-and-fire neuron array transceiver with a multi-modal neuron architecture is presented. The design features an array of 16 × 16 charge-mode mixed-signal neurons that can be configured to implement a variety of activation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::981c895edb8d61668ab131859ffdb33f
https://doi.org/10.1145/3407197.3407209
https://doi.org/10.1145/3407197.3407209
Autor:
Huaqiang Wu, Priyanka Raina, Rajkumar Kubendran, H.-S. Philip Wong, Siddharth Josbi, Bin Gao, Gert Cauwenberghs, Weier Wan
Publikováno v:
2020 IEEE Symposium on VLSI Technology.
The energy efficiency of RRAM-based in-memory matrix-vector multiplication (MVM) depends largely on the output sensing mechanism. We design a novel voltage-mode sensing configuration with differential-row weight mapping that achieves a 3.6x improveme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ebd1620e288e987807679bad708d0454
https://doi.org/10.1109/vlsitechnology18217.2020.9265066
https://doi.org/10.1109/vlsitechnology18217.2020.9265066
Autor:
Huaqiang Wu, Bin Gao, S. Burc Eryilmaz, Priyanka Raina, Gert Cauwenberghs, Yan Liao, Dabin Wu, Siddharth Joshi, Stephen R. Deiss, Weier Wan, Rajkumar Kubendran, Wenqiang Zhang, H.-S. Philip Wong
Publikováno v:
ISSCC
Many powerful neural network (NN) models such as probabilistic graphical models (PGMs) and recurrent neural networks (RNNs) require flexibility in dataflow and weight access patterns as shown in Fig. 33.1.1 Typically, Compute-In-Memory (CIM) designs
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5be3ee3ce6db6a424306d82c68020229
https://doi.org/10.1109/isscc19947.2020.9062979
https://doi.org/10.1109/isscc19947.2020.9062979
Autor:
Hsiang-Lan Lung, Weier Wan, Jesse Engel, Ryan Zarcone, Sangbum Kim, S. Burc Eryilmaz, H.-S. Philip Wong, Bruno A. Olshausen, Matthew J. BrightSky, Chung H. Lam
Publikováno v:
Scientific Reports
Scientific Reports, Vol 10, Iss 1, Pp 1-13 (2020)
Scientific Reports, Vol 10, Iss 1, Pp 1-13 (2020)
Exponential growth in data generation and large-scale data science has created an unprecedented need for inexpensive, low-power, low-latency, high-density information storage. This need has motivated significant research into multi-level memory devic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d69662193cd389702c1b566c528bba7
https://pubmed.ncbi.nlm.nih.gov/32747716
https://pubmed.ncbi.nlm.nih.gov/32747716
Autor:
Dylan M. Paiton, Joon Sohn, Weier Wan, Ryan Zarcone, H.-S. Philip Wong, Bruno A. Olshausen, Xin Zheng
Publikováno v:
2018 IEEE International Electron Devices Meeting (IEDM).
We demonstrate by experiment an image storage and compression task by directly storing analog image data onto an analog-valued RRAM array. A joint source-channel coding algorithm is developed with a neural network to encode and retrieve natural image
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5090bad709c781a4ccaec754a5a8b2f1
https://doi.org/10.1109/iedm.2018.8614612
https://doi.org/10.1109/iedm.2018.8614612
Publikováno v:
2018 IEEE Symposium on VLSI Technology.
Resistive cross-point array can be used to implement vector-matrix multiplication in analog fashion. However, the output is in the form of analog current, and thus requires A/D conversion prior to digital storage. This paper develops and demonstrates
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6d54c7c62c9ccb67ee92c47e17afc58
https://doi.org/10.1109/vlsit.2018.8510634
https://doi.org/10.1109/vlsit.2018.8510634
Publikováno v:
ISCAS
As two-dimensional scaling of Si CMOS crosses the nanometer threshold, from 7 nm, 5 nm, 3 nm, toward 1 nm technology nodes, will it continue to provide the energy efficiency required of future computing systems? A scalable, fast, and energy-efficient
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9b799207d04e2caf3debb3c482d46778
https://doi.org/10.1109/iscas.2018.8351756
https://doi.org/10.1109/iscas.2018.8351756