Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Sang-Gyun Gi"'
Publikováno v:
IEEE Transactions on Industrial Electronics. 70:6442-6451
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::067393badaa45e687cb6d4f968c005fb
https://doi.org/10.1109/tie.2022.3190876
https://doi.org/10.1109/tie.2022.3190876
Publikováno v:
IEEE Transactions on Industrial Electronics. 68:11554-11564
This article presents a hardware- and power-efficient RRAM-based neural network capable of online learning. The network is modularized in consideration of scalability and consists of 11 modules. Each module comprises two 25 × 25 RRAM crossbar arrays
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c8046b6a6a9cd4329e8bf69db9caf3a3
https://doi.org/10.1109/tie.2020.3032867
https://doi.org/10.1109/tie.2020.3032867
Autor:
Donguk Lee, Byung-Geun Lee, Hyunsang Hwang, Chuljun Lee, Sang-Gyun Gi, Seokjae Lim, Wooseok Choi
Publikováno v:
IEEE Transactions on Nanotechnology. 19:594-600
Hardware neural networks (HNNs) which use synapse device (SD) arrays show promise as an approach to energy efficient parallel computation of massive vector-matrix multiplication. To maximize the inference accuracy of application-specific HNNs, we pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d7ae7bbed95c9399b39768947abaf2d
https://doi.org/10.1109/tnano.2020.3010070
https://doi.org/10.1109/tnano.2020.3010070
Publikováno v:
IEEE Transactions on Electron Devices. 66:2937-2945
In this study, a circuit technique and training algorithm that minimizes the effect of stuck-at-faults (SAFs) within a memristor crossbar array of neural networks (NNs) are presented. To improve the network performance in the presence of SAFs, a conv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a9af63d1595f1c97f78bf529d3540c1f
https://doi.org/10.1109/ted.2019.2914460
https://doi.org/10.1109/ted.2019.2914460
Publikováno v:
IEEE Transactions on Electron Devices. 65:3996-4003
This paper presents a new method for modeling the nonideal conductance response (CR) of synaptic devices. Unlike previous studies, which utilize physical device properties for modeling, this paper only uses the measured CR data. This allows the propo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6bed5a06299e9431869b1c4a672d6835
https://doi.org/10.1109/ted.2018.2858762
https://doi.org/10.1109/ted.2018.2858762
Publikováno v:
AICAS
This paper presents a circuit for spike-timing dependent plasticity (STDP) learning of a non-volatile memory (NVM) based spiking neural network (SNN). Unlike conventional hardware for implementation of STDP learning, the proposed circuit does not req
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8152a20dc4e309745b6078dcd339dc40
https://doi.org/10.1109/aicas.2019.8771602
https://doi.org/10.1109/aicas.2019.8771602
Publikováno v:
AICAS
A CMOS-based resistive computing element (RCE), which can be integrated in a crossbar array, is presented. The RCE successfully solves the hardware constraints of the existing memristive devices such as dynamic ranges of conductance, I-V nonlinearity
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9453df59bcbe814c77507d9dc9794d3a
https://doi.org/10.1109/aicas.2019.8771576
https://doi.org/10.1109/aicas.2019.8771576
Autor:
Myonglae Chu, Hyunsang Hwang, Jaesung Park, Euijun Cha, Byung-Geun Lee, Sang Ho Oh, Kyungjoon Baek, Sang-Gyun Gi, Kibong Moon
Publikováno v:
IEEE Electron Device Letters. 37:1067-1070
This letter presents an investigation of analog synapse characteristics of a PCMO-based interface switching device with varying electrode materials. In comparison with the filamentary switching device having only 1-b storage and variability issues, t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f22862298569d27efaeb6789da2a77de
https://doi.org/10.1109/led.2016.2583545
https://doi.org/10.1109/led.2016.2583545
Publikováno v:
BioCAS
One of the key elements in an artificial neural networks (ANNs) is the activation function (AF), that converts the weighted sum of a neuron's input into a probability of firing rate. The hardware implementation of the AF requires complicated circuits
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fffc3142315d92205609192d92273b80
https://doi.org/10.1109/biocas.2016.7833826
https://doi.org/10.1109/biocas.2016.7833826
Autor:
Myonglae Chu, Euijun Cha, Byung-Geun Lee, Kyungjoon Baek, Jaesung Park, Hyunsang Hwang, Sang Ho Oh, Sang-Gyun Gi, Kibong Moon
Publikováno v:
2015 IEEE International Electron Devices Meeting (IEDM).
We report novel nanoscale synapse and neuron devices for ultra-high density neuromorphic system. By adopting a Mo electrode, the redox reaction at Mo/Pr0.7Ca0.3MnO3 (PCMO) interface was controlled which in turn significantly improve synapse character
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ddcb1c77732c18034ec294f16428e299
https://doi.org/10.1109/iedm.2015.7409721
https://doi.org/10.1109/iedm.2015.7409721