Search Results for author: HyungJun Kim

Found 9 papers, 2 papers with code

INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold

no code implementations15 Apr 2022 Changhun Lee, HyungJun Kim, Eunhyeok Park, Jae-Joon Kim

We argue that using statistical data from a batch fails to capture the crucial information for each input instance in BNN computations, and the differences between statistical information computed from each instance need to be considered when determining the binary activation threshold of each instance.

Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution

no code implementations CVPR 2021 HyungJun Kim, Jihoon Park, Changhun Lee, Jae-Joon Kim

We also show that adjusting the threshold values of binary activation functions results in the unbalanced distribution of the binary activation, which increases the accuracy of BNN models.


SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System

no code implementations22 Sep 2020 Hwaran Lee, Seokhwan Jo, HyungJun Kim, SangKeun Jung, Tae-Yoon Kim

To our best knowledge, our work is the first comprehensive study of a modularized E2E multi-domain dialog system that learning from each component to the entire dialog policy for task success.

reinforcement-learning Reinforcement Learning (RL)

Empirical Strategy for Stretching Probability Distribution in Neural-network-based Regression

no code implementations8 Sep 2020 Eunho Koo, HyungJun Kim

In this study, we considered the distribution error, i. e., the inconsistency of two distributions (those of the predicted values and label), as the prediction error, and proposed weighted empirical stretching (WES) as a novel loss function to increase the overlap area of the two distributions.


BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations

1 code implementation ICLR 2020 Hyungjun Kim, Kyung-Su Kim, Jinseok Kim, Jae-Joon Kim

Binary Neural Networks (BNNs) have been garnering interest thanks to their compute cost reduction and memory savings.

Zero-shifting Technique for Deep Neural Network Training on Resistive Cross-point Arrays

no code implementations24 Jul 2019 Hyungjun Kim, Malte Rasch, Tayfun Gokmen, Takashi Ando, Hiroyuki Miyazoe, Jae-Joon Kim, John Rozen, Seyoung Kim

By using this zero-shifting method, we show that network performance dramatically improves for imbalanced synapse devices.

BitSplit-Net: Multi-bit Deep Neural Network with Bitwise Activation Function

no code implementations23 Mar 2019 Hyungjun Kim, Yulhwa Kim, Sungju Ryu, Jae-Joon Kim

We demonstrate that the BitSplit version of LeNet-5, VGG-9, AlexNet, and ResNet-18 can be trained to have similar classification accuracy at a lower computational cost compared to conventional multi-bit networks with low bit precision (<= 4-bit).

Neural Network-Hardware Co-design for Scalable RRAM-based BNN Accelerators

1 code implementation6 Nov 2018 Yulhwa Kim, HyungJun Kim, Jae-Joon Kim

Recently, RRAM-based Binary Neural Network (BNN) hardware has been gaining interests as it requires 1-bit sense-amp only and eliminates the need for high-resolution ADC and DAC.

Neural Network simulation

Deep Neural Network Optimized to Resistive Memory with Nonlinear Current-Voltage Characteristics

no code implementations30 Mar 2017 Hyungjun Kim, Taesu Kim, Jinseok Kim, Jae-Joon Kim

Artificial Neural Network computation relies on intensive vector-matrix multiplications.

Cannot find the paper you are looking for? You can Submit a new open access paper.