National Yang Ming Chiao Tung Uni.(NYCU)
MSc in Statistics
Taipei, Taiwan
Jan. 2024 - Jun. 2024
Stockholm, Sweden
In this project, I combine the counterfactual explanation technique (specifically DiCE) with the rule extraction algorithm (Discretized Bayes Rule extraction) to extract understandable rules from a black box AI model.
Aug. 2023 - Jun. 2024
2021 - 2023
2017 - 2021
We have used the PyTorch framework to reproduce a semi-supervised multi-object segmentation model, which extends the Masked Autoencoder. The authors have incorporated a Siamese network into the Masked Autoencoder, enabling it to outperform some state-of-the-art (SOTA) models like VideoMAE and Dino.
My contribution:
Model Building and Validation: Responsible for constructing, evaluating, and visualizing the results of our models to ensure accuracy and efficiency.
First year at NYCU
We used deep learning and ANVIL's product to create an interactive interface.
My contribution:
First year at NYCU
We built an image recognition deep learning model to do the self-driving car simulation.
My contribution:
We implement several statistical-based machine learning methods to predict whether the customers will subscribe to the deposit service or not.
My contribution:
We used R to implement a spatial statistical prediction method called Kriging to analyze the shooting hot zone of NBA players.
My contribution:
National Yang Ming Chiao Tung Uni.(NYCU)
MSc in Statistics
Taipei, Taiwan
Jan. 2024 - Jun. 2024
Stockholm, Sweden
In this project, I combine the counterfactual explanation technique (specifically DiCE) with the rule extraction algorithm (Discretized Bayes Rule extraction) to extract understandable rules from a black box AI model.
Aug. 2023 - Jun. 2024
2021 - 2023
2017 - 2021
We have used the PyTorch framework to reproduce a semi-supervised multi-object segmentation model, which extends the Masked Autoencoder. The authors have incorporated a Siamese network into the Masked Autoencoder, enabling it to outperform some state-of-the-art (SOTA) models like VideoMAE and Dino.
My contribution:
Model Building and Validation: Responsible for constructing, evaluating, and visualizing the results of our models to ensure accuracy and efficiency.
First year at NYCU
We used deep learning and ANVIL's product to create an interactive interface.
My contribution:
First year at NYCU
We built an image recognition deep learning model to do the self-driving car simulation.
My contribution:
We implement several statistical-based machine learning methods to predict whether the customers will subscribe to the deposit service or not.
My contribution:
We used R to implement a spatial statistical prediction method called Kriging to analyze the shooting hot zone of NBA players.
My contribution: