Follow
Jaeha Kung
Jaeha Kung
Associate Professor, Korea University
Verified email at korea.ac.kr
Title
Cited by
Cited by
Year
Neurocube: A programmable digital neuromorphic architecture with high-density 3D memory
D Kim, J Kung, S Chai, S Yalamanchili, S Mukhopadhyay
ACM SIGARCH Computer Architecture News 44 (3), 380-392, 2016
4962016
On-chip training of recurrent neural networks with limited numerical precision
T Na, JH Ko, J Kung, S Mukhopadhyay
2017 International Joint Conference on Neural Networks (IJCNN), 3716-3723, 2017
502017
Adaptive weight compression for memory-efficient neural networks
JH Ko, D Kim, T Na, J Kung, S Mukhopadhyay
Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017 ・, 2017
472017
A power-aware digital multilayer perceptron accelerator with on-chip training based on approximate computing
D Kim, J Kung, S Mukhopadhyay
IEEE Transactions on Emerging Topics in Computing 5 (2), 164-178, 2017
472017
A power-aware digital feedforward neural network platform with backpropagation driven approximate synapses
J Kung, D Kim, S Mukhopadhyay
2015 IEEE/ACM International Symposium on Low Power Electronics and Design ・, 2015
452015
Efficient object detection using embedded binarized neural networks
J Kung, D Zhang, G Van der Wal, S Chai, S Mukhopadhyay
Journal of Signal Processing Systems 90, 877-890, 2018
392018
Design and analysis of approximate compressors for balanced error accumulation in MAC operator
G Park, J Kung, Y Lee
IEEE Transactions on Circuits and Systems I: Regular Papers 68 (7), 2950-2961, 2021
332021
Reram crossbar based recurrent neural network for human activity detection
Y Long, EM Jung, J Kung, S Mukhopadhyay
2016 international joint conference on neural networks (IJCNN), 939-946, 2016
302016
On the Impact of Energy-Accuracy Tradeoff in a Digital Cellular Neural Network for Image Processing
J Kung, D Kim, S Mukhopadhyay
IEEE Transactions on Computer-Aided Design of Integrated Circuits and ・, 2015
302015
Approximate LSTM computing for energy-efficient speech recognition
J Jo, J Kung, Y Lee
Electronics 9 (12), 2004, 2020
282020
Maximizing system performance by balancing computation loads in LSTM accelerators
J Park, J Kung, W Yi, JJ Kim
2018 Design, Automation & Test in Europe Conference & Exhibition (DATE), 7-12, 2018
262018
Dynamic approximation with feedback control for energy-efficient recurrent neural network hardware
J Kung, D Kim, S Mukhopadhyay
Proceedings of the 2016 International Symposium on Low Power Electronics and ・, 2016
182016
Thermal signature: A simple yet accurate thermal index for floorplan optimization
J Kung, I Han, S Sapatnekar, Y Shin
Proceedings of the 48th Design Automation Conference, 108-113, 2011
182011
A Programmable Hardware Accelerator for Simulating Dynamical Systems
J Kung, Y Long, D Kim, S Mukhopadhyay
Computer Architecture (ISCA), 2017 ACM/IEEE 44th Annual International ・, 2017
172017
NeuroSensor: A 3D image sensor with integrated neural accelerator
MF Amir, D Kim, J Kung, D Lie, S Yalamanchili, S Mukhopadhyay
2016 IEEE SOI-3D-Subthreshold Microelectronics Technology Unified Conference ・, 2016
172016
Peregrine: A flexible hardware accelerator for LSTM with limited synaptic connection patterns
J Kung, J Park, S Park, JJ Kim
Proceedings of the 56th Annual Design Automation Conference (DAC) 2019, 2019
122019
Similarity-based LSTM architecture for energy-efficient edge-level speech recognition
J Jo, J Kung, S Lee, Y Lee
2019 IEEE/ACM International Symposium on Low Power Electronics and Design ・, 2019
112019
Balancing Computation Loads and Optimizing Input Vector Loading in LSTM Accelerators
J Park, W Yi, D Ahn, J Kung, JJ Kim
IEEE Transactions on Computer-Aided Design of Integrated Circuits and ・, 2019
102019
FlexBlock: A flexible DNN training accelerator with multi-mode block floating point support
SH Noh, J Koo, S Lee, J Park, J Kung
IEEE Transactions on Computers, 2023
92023
High-throughput near-memory processing on CNNs with 3D HBM-like memory
N Park, S Ryu, J Kung, JJ Kim
ACM Transactions on Design Automation of Electronic Systems (TODAES) 26 (6 ・, 2021
82021
The system can't perform the operation now. Try again later.
Articles 1–20