Current Position: AI Team - Software Engineer at the Central Weather Bureau, specializing in machine learning. Tasks include image generation, numerical prediction, data calibration, recommendation systems, and text generation using data from satellites, radar, and geographic information.
I stay updated on AI advancements by studying research papers and implementing new approaches into projects. Recently, I've focused on deploying Large Language Models (LLM) in customer-oriented chatbots.
Proficient in Docker for establishing and maintaining development environments, deploying projects to client environments.
Previous experience as a data analyst in R&D, conducting big data analysis and applying machine learning for data calibration at an instrument manufacturing company.
Holder of a master's degree in Environmental Engineering with expertise in statistical software (R, Python, ArcGIS, VBA) for data crawling, big data analysis, and geographic information mapping.
Deep model architecture building experience
built the architecture of various generative models:BASNET, DCGAN, VQ-VAE, DANET, SPNET.
Used plug-and-play modules:Resblock, GhostBottleNeck, SE-layer, DarkBlock.
Used Attention mechanism:StripPooling, MixedPoolingModule, SelectiveKernel.
According to the input data, use convolutional layers of different dimensions (1D~3D) to learn information.
Used weight standardization to assign weights to improve model training effect.
Built a composite model of regression and classification.
AI development environment management
Used docker or Anaconda to establish and maintain the development environment with GPU.
Set up the environment to use the LLM (LLAMA2, Taiwan-LLaMa, Codellama, Llama2-chinese-13b, etc.)
Model Training and Tuning Tips
Adjusted the data batch size according to the hardware performance, and adjusted the normalization method in hidden layers.
Used Microsoft nni to adjust hyperparameters during model architecture and training.
Combined with Explainable AI methods in the training process.
Trained with Optuna and TPOT in machine learning projects.
Statistics Checking Skills
Regression model
R-squared, RMSE, MAE, Residual Analysis, Correlation, POD, FAR, etc.
Classification model
ROC curve, AUC, Confusion Matrix, F1-score, recall.
Image Generation - Rainfall Map Prediction & Air Force Radar Map Prediction
Image Recognition - Typhoon Intensity Detection
Numerical Prediction - System Monitoring and Anomaly Detection
Recommendation System - Host Associations in Anomalous Cases
Data Clustering & Text Parsing - Error Message Recommendation System
Numerical Calibration - Small Projects with AutoML Tools
Natural Language Processing & Large Language Model Application - Generating Forecast Text
Large Language Model Application - LLAMA Open Source Model Application
Establishing, Deploying, and Maintaining Development Environments - Docker, Anaconda
Programming:
Data Calibration - Machine Learning:
Web Scraping:
Documentation:
Sep 2016 - Jul 2017
Apr 2012 - Jul 2016
Current Position: AI Team - Software Engineer at the Central Weather Bureau, specializing in machine learning. Tasks include image generation, numerical prediction, data calibration, recommendation systems, and text generation using data from satellites, radar, and geographic information.
I stay updated on AI advancements by studying research papers and implementing new approaches into projects. Recently, I've focused on deploying Large Language Models (LLM) in customer-oriented chatbots.
Proficient in Docker for establishing and maintaining development environments, deploying projects to client environments.
Previous experience as a data analyst in R&D, conducting big data analysis and applying machine learning for data calibration at an instrument manufacturing company.
Holder of a master's degree in Environmental Engineering with expertise in statistical software (R, Python, ArcGIS, VBA) for data crawling, big data analysis, and geographic information mapping.
Deep model architecture building experience
built the architecture of various generative models:BASNET, DCGAN, VQ-VAE, DANET, SPNET.
Used plug-and-play modules:Resblock, GhostBottleNeck, SE-layer, DarkBlock.
Used Attention mechanism:StripPooling, MixedPoolingModule, SelectiveKernel.
According to the input data, use convolutional layers of different dimensions (1D~3D) to learn information.
Used weight standardization to assign weights to improve model training effect.
Built a composite model of regression and classification.
AI development environment management
Used docker or Anaconda to establish and maintain the development environment with GPU.
Set up the environment to use the LLM (LLAMA2, Taiwan-LLaMa, Codellama, Llama2-chinese-13b, etc.)
Model Training and Tuning Tips
Adjusted the data batch size according to the hardware performance, and adjusted the normalization method in hidden layers.
Used Microsoft nni to adjust hyperparameters during model architecture and training.
Combined with Explainable AI methods in the training process.
Trained with Optuna and TPOT in machine learning projects.
Statistics Checking Skills
Regression model
R-squared, RMSE, MAE, Residual Analysis, Correlation, POD, FAR, etc.
Classification model
ROC curve, AUC, Confusion Matrix, F1-score, recall.
Image Generation - Rainfall Map Prediction & Air Force Radar Map Prediction
Image Recognition - Typhoon Intensity Detection
Numerical Prediction - System Monitoring and Anomaly Detection
Recommendation System - Host Associations in Anomalous Cases
Data Clustering & Text Parsing - Error Message Recommendation System
Numerical Calibration - Small Projects with AutoML Tools
Natural Language Processing & Large Language Model Application - Generating Forecast Text
Large Language Model Application - LLAMA Open Source Model Application
Establishing, Deploying, and Maintaining Development Environments - Docker, Anaconda
Programming:
Data Calibration - Machine Learning:
Web Scraping:
Documentation:
Sep 2016 - Jul 2017
Apr 2012 - Jul 2016