no code implementations • EMNLP (ECONLP) 2021 • Kyunghwan Sohn, Sunjae Kwon, Jaesik Choi
A domain specific question answering (QA) dataset dramatically improves the machine comprehension performance.
no code implementations • 22 Mar 2024 • Hyunkyung Han, Jaesik Choi
To address these limitations, we replaced the attention mechanism in the GPT model with a pointer network.
no code implementations • 20 Mar 2024 • Soyeon Kim, Jihyeon Seong, Hyunkyung Han, Jaesik Choi
In this paper, we investigate the effectiveness of CapsNets in analyzing highly sensitive and noisy time series sensor data.
1 code implementation • 14 Mar 2024 • Hyunkyung Han, Jihyeon Seong, Jaesik Choi
In this paper, we explore the potential of DR-CapsNets and propose CardioCaps, a novel attention-based DR-CapsNet architecture for class-imbalanced echocardiogram classification.
no code implementations • 14 Mar 2024 • Jihyeon Seong, Jungmin Kim, Jaesik Choi
In this paper, we propose a novel temporal pooling method with diverse perspective learning: Selection over Multiple Temporal Poolings (SoM-TP).
2 code implementations • 28 Dec 2023 • Wonjoon Chang, Dahee Kwon, Jaesik Choi
Understanding intermediate representations of the concepts learned by deep learning classifiers is indispensable for interpreting general model behaviors.
1 code implementation • NeurIPS 2023 • Kyowoon Lee, Seongun Kim, Jaesik Choi
We also illustrate that our approach presents explainability by presenting the attribution maps of the gap predictor and highlighting error-prone transitions, allowing for a deeper understanding of the generated plans.
1 code implementation • 30 Oct 2023 • Seongun Kim, Kyowoon Lee, Jaesik Choi
We validate the effectiveness of our approach on complex navigation and robotic manipulation tasks in terms of sample efficiency and state coverage speed.
no code implementations • 30 Oct 2023 • Seongun Kim, Jaesik Choi
In this paper, we present an explicit analysis of deep policy models through input attribution methods to explain how and to what extent each input feature affects the decisions of the robot policy models.
no code implementations • 30 Oct 2023 • Luca Longo, Mario Brcic, Federico Cabitza, Jaesik Choi, Roberto Confalonieri, Javier Del Ser, Riccardo Guidotti, Yoichi Hayashi, Francisco Herrera, Andreas Holzinger, Richard Jiang, Hassan Khosravi, Freddy Lecue, Gianclaudio Malgieri, Andrés Páez, Wojciech Samek, Johannes Schneider, Timo Speith, Simone Stumpf
As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
1 code implementation • 24 Oct 2023 • Ye Eun Chun, Sunjae Kwon, Kyunghwan Sohn, Nakwon Sung, Junyoup Lee, Byungki Seo, Kevin Compher, Seung-won Hwang, Jaesik Choi
In this paper, we introduce CR-COPEC called Causal Rationale of Corporate Performance Changes from financial reports.
1 code implementation • 20 Oct 2023 • Anh Tong, Thanh Nguyen-Tang, Dongeun Lee, Toan Tran, Jaesik Choi
To mitigate such difficulties, we introduce SigFormer, a novel deep learning model that combines the power of path signatures and transformers to handle sequential data, particularly in cases with irregularities.
1 code implementation • 12 Oct 2023 • Cheongwoong Kang, Jaesik Choi
Consequently, LLMs struggle to recall facts whose subject and object rarely co-occur in the pre-training dataset although they are seen during finetuning.
no code implementations • 23 Apr 2023 • Inyoung Paik, Jaesik Choi
In this study, we analyze the occurrence and mitigation of gradient explosion both theoretically and empirically, and discover that the correlation between activations plays a key role in preventing the gradient explosion from persisting throughout the training.
no code implementations • 22 Feb 2023 • Nesma Mahmoud, Hanna Antson, Jaesik Choi, Osamu Shimmi, Kallol Roy
In our paper, we have generated artificial perturbations to our model by hot-swapping the activation and loss functions during the training.
no code implementations • ICCV 2023 • Giyoung Jeon, Haedong Jeong, Jaesik Choi
We show that such noisy attribution can be reduced by aggregating attributions from the multiple paths instead of using a single path.
no code implementations • 18 Nov 2022 • Bumjin Park, Jaesik Choi
As the number of fine tuning of pretrained models increased, understanding the bias of pretrained model is essential.
1 code implementation • 1 Sep 2022 • Sunjae Kwon, Cheongwoong Kang, Jiyeon Han, Jaesik Choi
We exemplify the possibility to overcome the limitations of the MNLM-based RC models by enriching text with the required knowledge from an external commonsense knowledge repository in controlled experiments.
no code implementations • 7 Jul 2022 • SeongJin Park, Haedong Jeong, Giyoung Jeon, Jaesik Choi
In general, Deep Neural Networks (DNNs) are evaluated by the generalization performance measured on unseen data excluded from the training phase.
1 code implementation • 17 Jun 2022 • Jiyeon Han, Hwanil Choi, Yunjey Choi, Junho Kim, Jung-Woo Ha, Jaesik Choi
In this work, we propose a new evaluation metric, called `rarity score', to measure the individual rarity of each image synthesized by generative models.
no code implementations • 17 Feb 2022 • Deokjun Eom, Sehyun Lee, Jaesik Choi
The intensity functions are computed using the distribution of latent variable so that we can predict event types and the arrival times of the events more accurately.
1 code implementation • 17 Jan 2022 • Hwanil Choi, Wonjoon Chang, Jaesik Choi
Even though Generative Adversarial Networks (GANs) have shown a remarkable ability to generate high-quality images, GANs do not always guarantee the generation of photorealistic images.
no code implementations • 16 Dec 2021 • Haedong Jeong, Jiyeon Han, Jaesik Choi
Despite significant improvements on the image generation performance of Generative Adversarial Networks (GANs), generations with low visual fidelity still have been observed.
no code implementations • 29 Sep 2021 • Daehoon Gwak, Gyubok Lee, Jaehoon Lee, Jaesik Choi, Jaegul Choo, Edward Choi
To address this, we introduce a new neural stochastic processes, Decoupled Kernel Neural Processes (DKNPs), which explicitly learn a separate mean and kernel function to directly model the covariance between output variables in a data-driven manner.
no code implementations • 29 Sep 2021 • SeongJin Park, Haedong Jeong, Giyoung Jeon, Jaesik Choi
In general, the Deep Neural Networks (DNNs) is evaluated by the generalization performance measured on the unseen data excluded from the training phase.
1 code implementation • ICML 2021 • Boseon Yoo, Jiwoo Lee, Janghoon Ju, Seijun Chung, Soyeon Kim, Jaesik Choi
We introduce a novel loss function, Covariance Loss, which is conceptually equivalent to conditional neural processes and has a form of regularization so that is applicable to many kinds of neural networks.
Ranked #1 on Time Series Forecasting on PeMSD7
no code implementations • CVPR 2021 • Ali Tousi, Haedong Jeong, Jiyeon Han, Hwanil Choi, Jaesik Choi
Generative Adversarial Networks (GANs) have shown satisfactory performance in synthetic image generation by devising complex network structure and adversarial training scheme.
no code implementations • 21 Dec 2020 • Anh Tong, Toan Tran, Hung Bui, Jaesik Choi
Choosing a proper set of kernel functions is an important problem in learning Gaussian Process (GP) models since each kernel structure has different model complexity and data fitness.
no code implementations • 7 Dec 2020 • Woo-Jeoung Nam, Jaesik Choi, Seong-Whan Lee
As a result, it is possible to assign the bi-polar relevance scores of the target (positive) and hostile (negative) attributions while maintaining each attribution aligned with the importance.
no code implementations • 19 Oct 2020 • Anh Tong, Jaesik Choi
Recent advances in Deep Gaussian Processes (DGPs) show the potential to have more expressive representation than that of traditional Gaussian Processes (GPs).
no code implementations • 16 Oct 2020 • YoungJin Park, Deokjun Eom, Byoungki Seo, Jaesik Choi
We reveal that the predictive performance of deep temporal neural networks improves when the training data is temporally processed by a trend filtering.
no code implementations • 27 Apr 2020 • Sohee Cho, Ginkyeng Lee, Wonjoon Chang, Jaesik Choi
Recently deep neural networks demonstrate competitive performances in classification and regression tasks for many temporal or sequential data.
no code implementations • 12 Dec 2019 • Giyoung Jeon, Haedong Jeong, Jaesik Choi
Despite of recent advances in generative networks, identifying the image generation mechanism still remains challenging.
no code implementations • 8 Nov 2019 • Sunjae Kwon, Cheongwoong Kang, Jiyeon Han, Jaesik Choi
From the test, we observed that MNLMs partially understand various types of common sense knowledge but do not accurately understand the semantic meaning of relations.
no code implementations • 16 Sep 2019 • Dongwon Park, Yonghyeok Seo, Dongju Shin, Jaesik Choi, Se Young Chun
Recently, robotic grasp detection (GD) and object detection (OD) with reasoning have been investigated using deep neural networks (DNNs).
no code implementations • 30 May 2019 • Jiyeon Han, Kyowoon Lee, Anh Tong, Jaesik Choi
We also provide conditions under which CBOCPD provides the lower prediction error compared to BOCPD.
1 code implementation • 1 Apr 2019 • Woo-Jeoung Nam, Shir Gur, Jaesik Choi, Lior Wolf, Seong-Whan Lee
As Deep Neural Networks (DNNs) have demonstrated superhuman performance in a variety of fields, there is an increasing interest in understanding the complex internal mechanisms of DNNs.
1 code implementation • ICML 2018 • Kyowoon Lee, Sol-A Kim, Jaesik Choi, Seong-Whan Lee
Many real-world applications of reinforcement learning require an agent to select optimal actions from continuous spaces.
no code implementations • ICLR 2018 • Thanh T. Nguyen, Jaesik Choi
Here, we propose Parametric Information Bottleneck (PIB) for a neural network by utilizing (only) its model parameters explicitly to approximate the compression and the relevance.
no code implementations • 4 Dec 2017 • Thanh T. Nguyen, Jaesik Choi
Information Bottleneck (IB) is a generalization of rate-distortion theory that naturally incorporates compression and relevance trade-offs for learning.
no code implementations • 29 Mar 2017 • Subin Yi, Janghoon Ju, Man-Ki Yoon, Jaesik Choi
In experiments with two real-world datasets, we demonstrate that our group CNNs outperform existing CNN based regression methods.
no code implementations • 28 Mar 2017 • Anh Tong, Jaesik Choi
In this paper, we present a new GP model which naturally handles multiple time series by placing an Indian Buffet Process (IBP) prior on the presence of shared kernels.
no code implementations • 27 Mar 2017 • Rafael Lima, Jaesik Choi
We demonstrate that the new automatic kernel decomposition procedure outperforms the existing methods on the prediction of discrete events in real-world data.
no code implementations • 4 Jul 2016 • Anh Tong, Jaesik Choi
In this paper, we provide a new perspective to build expressive probabilistic program from continue time series data when the structure of model is not given.
no code implementations • 11 Mar 2016 • Kallol Roy, Anh Tong, Jaesik Choi
To compute the symmetry in a grid structure, we introduce three legal grid moves (i) Commutation (ii) Cyclic Permutation (iii) Stabilization on sets of local grid squares, grid blocks.
no code implementations • 12 Feb 2016 • Vladimir Nekrasov, Janghoon Ju, Jaesik Choi
Semantic image segmentation is a principal problem in computer vision, where the aim is to correctly classify each individual pixel of an image into a semantic label.
no code implementations • 26 Nov 2015 • Yunseong Hwang, Anh Tong, Jaesik Choi
Gaussian Processes (GPs) provide a general and analytically tractable way of modeling complex time-varying, nonparametric functions.