游勤葑 Chin Feng Yu

Data Scientist 

  Taiwan

[email protected]

研究 Deep learning & Adversarial training & Active Learning
玉山人工智慧公開挑戰賽2019秋季賽第二名
多年資料處理以及機器學習與深度學習建模的經驗




學歷

2021 - 2022

國立政治大學

資訊科學所

2019 - 2021

國立彰化師範大學

資訊管理系

Top Conference Paper Publication

C. -F. Yu and H. -K. Pao, "Virtual Adversarial Active Learning," 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA, 2020, pp. 5323-5331, doi: 10.1109/BigData50022.2020.9378021


Abstract—In traditional active learning, one of the most well-known strategies is to select the most uncertain data for annotation. By doing that, we acquire as most as we can obtain from the labeling oracle so that the training in the next run can be much more effective than the one from this run once the informative labeled data are added to the training. The strategy, however, may not be suitable when deep learning becomes one of the dominant modeling techniques. Deep learning is notorious for its failure to achieve a certain degree of effectiveness under the adversarial environment. Often we see the sparsity in deep learning training space which gives us a result with low confidence. Moreover, to have some adversarial inputs to fool the deep learners, we should have an active learning strategy that can deal with the aforementioned difficulties. We propose a novel Active Learning strategy based on Virtual Adversarial Training (VAT) and the computation of local distributional roughness (LDR). Instead of selecting the data that are closest to the decision boundaries, we select the data that is located in a place with rough enough surface if measured by the posterior probability. The proposed strategy called Virtual Adversarial Active Learning (VAAL) can help us to find the data with rough surface, reshape the model with smooth posterior distribution output thanks to the active learning framework. Moreover, we shall prefer the labeling data that own enough confidence once they are annotated from an oracle. In VAAL, we have the VAT that can not only be used as a regularization term but also helps us effectively and actively choose the valuable samples for active learning labeling. Experiment results show that the proposed VAAL strategy can guide the convolutional networks model converging efficiently on several well-known datasets. 
Keywords: Active Learning, Adversarial Examples, Virtual Adversarial Training, Adversarial Training


工作經歷

二月 2021 - 六月 2021

AI QA實習生

訊連科技股份有限公司

 The beta test for FaceMe® Security


產學專案

三月 2021 - 7月 2021

台大醫院神經科--Parkinson Disease Detection

三月 2021 - 7月 2021

KaiKuTeK 手勢辨識


技能

Web Design

HTML, CSS, Javascript, Django


Machine Learning

Tensorflow & Keras 

Semi-Supervised/ Supervised / Unsupervised Learning 

Anomaly Detection, Object Detection

Others

C++

Java

Python


比賽經驗


玉山人工智慧公開挑戰賽2019秋季賽 第二名


校園專案-外匯車銷售平台

利用 Python Django 打造外匯車銷售網頁

建置 ER model ,後台管理者Dashboard

網頁設計美化 




校園專案-人臉辨識門禁管理

 因應疫情打造一個以人臉辨識為基礎的門禁系統, 此門禁系統會連動學校的健康以及旅遊史資料庫, 經過門禁系統使自動調閱學生的旅遊史。