Models, code, and papers for "Sangwon Im":

A Scalable Chatbot Platform Leveraging Online Community Posts: A Proof-of-Concept Study

Jan 10, 2020
Sihyeon Jo, Sangwon Im, SangWook Han, Seung Hee Yang, Hee-Eun Kim, Seong-Woo Kim

The development of natural language processing algorithms and the explosive growth of conversational data are encouraging researches on the human-computer conversation. Still, getting qualified conversational data on a large scale is difficult and expensive. In this paper, we verify the feasibility of constructing a data-driven chatbot with processed online community posts by using them as pseudo-conversational data. We argue that chatbots for various purposes can be built extensively through the pipeline exploiting the common structure of community posts. Our experiment demonstrates that chatbots created along the pipeline can yield the proper responses.

* To be Published on the 10th February, 2020, in HCI (Human-Computer Interaction) Conference 2020, Republic of Korea 

  Click for Model/Code and Paper
Interpretation and Simplification of Deep Forest

Jan 14, 2020
Sangwon Kim, Mira Jeong, Byoung Chul Ko

This paper proposes a new method for interpreting and simplifying a black box model of a deep random forest (RF) using a proposed rule elimination. In deep RF, a large number of decision trees are connected to multiple layers, thereby making an analysis difficult. It has a high performance similar to that of a deep neural network (DNN), but achieves a better generalizability. Therefore, in this study, we consider quantifying the feature contributions and frequency of the fully trained deep RF in the form of a decision rule set. The feature contributions provide a basis for determining how features affect the decision process in a rule set. Model simplification is achieved by eliminating unnecessary rules by measuring the feature contributions. Consequently, the simplified model has fewer parameters and rules than before. Experiment results have shown that a feature contribution analysis allows a black box model to be decomposed for quantitatively interpreting a rule set. The proposed method was successfully applied to various deep RF models and benchmark datasets while maintaining a robust performance despite the elimination of a large number of rules.

* 10 pages 

  Click for Model/Code and Paper
Deep Learning-based Limited Feedback Designs for MIMO Systems

Dec 19, 2019
Jeonghyeon Jang, Hoon Lee, Sangwon Hwang, Haibao Ren, Inkyu Lee

We study a deep learning (DL) based limited feedback methods for multi-antenna systems. Deep neural networks (DNNs) are introduced to replace an end-to-end limited feedback procedure including pilot-aided channel training process, channel codebook design, and beamforming vector selection. The DNNs are trained to yield binary feedback information as well as an efficient beamforming vector which maximizes the effective channel gain. Compared to conventional limited feedback schemes, the proposed DL method shows an 1 dB symbol error rate (SER) gain with reduced computational complexity.

* to appear in IEEE Wireless Commun. Lett 

  Click for Model/Code and Paper
Quantization for Rapid Deployment of Deep Neural Networks

Oct 12, 2018
Jun Haeng Lee, Sangwon Ha, Saerom Choi, Won-Jo Lee, Seungwon Lee

This paper aims at rapid deployment of the state-of-the-art deep neural networks (DNNs) to energy efficient accelerators without time-consuming fine tuning or the availability of the full datasets. Converting DNNs in full precision to limited precision is essential in taking advantage of the accelerators with reduced memory footprint and computation power. However, such a task is not trivial since it often requires the full training and validation datasets for profiling the network statistics and fine tuning the networks to recover the accuracy lost after quantization. To address these issues, we propose a simple method recognizing channel-level distribution to reduce the quantization-induced accuracy loss and minimize the required image samples for profiling. We evaluated our method on eleven networks trained on the ImageNet classification benchmark and a network trained on the Pascal VOC object detection benchmark. The results prove that the networks can be quantized into 8-bit integer precision without fine tuning.

  Click for Model/Code and Paper
Training Deep Neural Network in Limited Precision

Oct 12, 2018
Hyunsun Park, Jun Haeng Lee, Youngmin Oh, Sangwon Ha, Seungwon Lee

Energy and resource efficient training of DNNs will greatly extend the applications of deep learning. However, there are three major obstacles which mandate accurate calculation in high precision. In this paper, we tackle two of them related to the loss of gradients during parameter update and backpropagation through a softmax nonlinearity layer in low precision training. We implemented SGD with Kahan summation by employing an additional parameter to virtually extend the bit-width of the parameters for a reliable parameter update. We also proposed a simple guideline to help select the appropriate bit-width for the last FC layer followed by a softmax nonlinearity layer. It determines the lower bound of the required bit-width based on the class size of the dataset. Extensive experiments on various network architectures and benchmarks verifies the effectiveness of the proposed technique for low precision training.

  Click for Model/Code and Paper
AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map

Jan 07, 2020
Joosung Lee, Sangwon Hwang, Kyungjae Lee, Woo Jin Kim, Junhyeop Lee, Tae-young Chung, Sangyoun Lee

Visual odometry is an essential key for a localization module in SLAM systems. However, previous methods require tuning the system to adapt environment changes. In this paper, we propose a learning-based approach for frame-to-frame monocular visual odometry estimation. The proposed network is only learned by disparity maps for not only covering the environment changes but also solving the scale problem. Furthermore, attention block and skip-ordering scheme are introduced to achieve robust performance in various driving environment. Our network is compared with the conventional methods which use common domain such as color or optical flow. Experimental results confirm that the proposed network shows better performance than other approaches with higher and more stable results.

* 5 pages, 5 figures, 2018.02 papers 

  Click for Model/Code and Paper