1 code implementation • 27 Oct 2023 • Son Nguyen, Mikel Lainsa, Hung Dao, Daeyoung Kim, Giang Nguyen
Given the modest size of the dataset and the highly deformable nature of the objects to be segmented, this challenge demands the application of robust data augmentation techniques and wisely-chosen deep learning architectures.
no code implementations • 25 Aug 2023 • Giang Nguyen, Valerie Chen, Anh Nguyen
Besides providing insights into how an image classifier makes its predictions, nearest-neighbor examples also help humans make more accurate decisions.
2 code implementations • 15 Jun 2023 • Giang Nguyen, Sumon Biswas, Hridesh Rajan
In order to demonstrate the effectiveness of our approach, we evaluated our approach on four fairness problems and 16 different ML models, and our results show a significant improvement over the baseline and existing bias mitigation techniques.
no code implementations • 2 Apr 2023 • Viet H. Pham, Thang M. Pham, Giang Nguyen, Long Nguyen, Dien Dinh
We also introduce a SentenceBERT-based filter to enhance the quality of augmenting data by retaining semantically similar sentence pairs.
no code implementations • 25 Nov 2022 • Giang Nguyen
Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life.
Continual Learning Explainable Artificial Intelligence (XAI) +1
1 code implementation • 26 Jul 2022 • Giang Nguyen, Mohammad Reza Taesiri, Anh Nguyen
Via a large-scale, human study on ImageNet and CUB, our correspondence-based explanations are found to be more useful to users than kNN explanations.
2 code implementations • 6 Dec 2021 • Giang Nguyen, Md Johir Islam, Rangeet Pan, Hridesh Rajan
Recent work on AutoML, more precisely neural architecture search (NAS), embodied by tools like Auto-Keras aims to solve this problem by essentially viewing it as a search problem where the starting point is a default CNN model, and mutation of this CNN model allows exploration of the space of CNN models to find a CNN model that will work best for the problem.
no code implementations • 23 Sep 2021 • Rui Yuan, S. Ali Pourmousavi, Wen L. Soong, Giang Nguyen, Jon A. R. Liisberg
In this paper, we seek to identify residential consumers based on their BTM equipment, mainly rooftop photovoltaic (PV) systems and electric heating, using imported/purchased energy data from utility meters.
1 code implementation • NeurIPS 2021 • Giang Nguyen, Daeyoung Kim, Anh Nguyen
Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications.
2 code implementations • 3 May 2020 • Giang Nguyen, Shuan Chen, Tae Joon Jun, Daeyoung Kim
Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life.
1 code implementation • 6 Jan 2020 • Giang Nguyen, Shuan Chen, Thao Do, Tae Joon Jun, Ho-Jin Choi, Daeyoung Kim
Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life.
1 code implementation • 19 Sep 2019 • Giang Nguyen, Tae Joon Jun, Trung Tran, Tolcha Yalew, Daeyoung Kim
After proving forgetting in image captioning, we propose various techniques to overcome the forgetting dilemma by taking a simple fine-tuning schema as the baseline.
1 code implementation • 19 Jun 2019 • Nigel Bean, Angus Lewis, Giang Nguyen
Markovian-regime-switching (MRS) models are commonly used for modelling economic time series, including electricity prices where independent regime models are used, since they can more accurately and succinctly capture electricity price dynamics than dependent regime MRS models can.
Methodology 62F10
no code implementations • 3 Jun 2019 • Md Johirul Islam, Giang Nguyen, Rangeet Pan, Hridesh Rajan
The key findings of our study include: data bug and logic bug are the most severe bug types in deep learning software appearing more than 48% of the times, major root causes of these bugs are Incorrect Model Parameter (IPS) and Structural Inefficiency (SI) showing up more than 43% of the times.
no code implementations • 12 Apr 2019 • John Boaz Lee, Giang Nguyen, Ryan A. Rossi, Nesreen K. Ahmed, Eunyee Koh, Sungchul Kim
In this work, we propose using the notion of temporal walks for learning dynamic embeddings from temporal networks.