EGpineapples (Elysia Gao) · GitHub
Skip to content
View EGpineapples's full-sized avatar

Block or report EGpineapples

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
EGpineapples/README.md

Elysia Gao

AI/ML Engineer & Data Scientist | End-to-End ML, From Research to Production 🛠️

About Me 🚀

Data Scientist and AI/ML Engineer with a strong background in Mathematical Modelling, Computation, and Chemical Engineering. Passionate about applying advanced machine learning and deep learning techniques to solve complex problems in biosustainability and urban mobility.

Skills 💻

  • Programming/Tools: Python (Pandas, Scikit-learn, NumPy), R, SQL, C/C++, TensorFlow, PyTorch, Docker, Git, Azure DevOps, Azure, Google Cloud, LangChain, Airflow, MLflow, Tableau, Streamlit, Power BI, DuckDB, Databricks, Spark, Redshift, Terraform
  • Machine Learning/Statistics: Forecasting, Deep Learning, NLP, Generative AI, LLMs (fine-tuning, RAG), Clustering, Anomaly Detection, Reinforcement Learning, Statistical Modeling (GLMs, A/B Testing)

Projects 🛠️

Spatio-Temporal Deep Learning Graph Neural Networks 🗺️

Python TensorFlow Graph Neural Networks Deep Learning

  • Developed an innovative deep learning model using Python, TensorFlow, and Graph Neural Networks
  • Implemented a Relational Graph Convolutional Variational Autoencoder with a Regression Network
  • Utilized Google Maps and Mapillary APIs for data extraction and feature engineering

Cell Lifelines Autoencoder 🧫

Python TensorFlow Pandas scikit-learn XGBoost R Autoencoders Clustering Classification

  • Developed and trained a custom TensorFlow & Python deep learning generative AI autoencoder (VAE) for time-series analysis
  • Achieved over 90% dimensionality reduction with less than 5% error in cell lifespan and metabolism analysis
  • Presented research on "Decoding Cell Behavior in Bioreactors: Deep Learning & Latent Space Insights" at a major symposium
  • Applied advanced data manipulation techniques using Pandas and machine learning models with scikit-learn
  • Implemented clustering, classification, and regression models on large-scale biological datasets

Fine-Tuning LLMs with Low Rank Adaptation (LoRA) 🤖

Python Hugging Face BERT NLP

  • Implemented LoRA on BERT's attention mechanism
  • Fine-tuned a bert-base-cased model on Yelp reviews using LoRA
  • Explored parameter-efficient fine-tuning techniques including prefix-tuning

Affiliations 🤝

  • Data Angels Women in Data Networking Group (Jan 2024 – Present)
  • Artificial Intelligence at the IT University of Copenhagen (AITU) Journal Club (Jan 2023 – Present)

Contact 📫

Pinned Loading

  1. Spatio-temporal-Graph-Neural-Networks-for-Emotion-Prediction Spatio-temporal-Graph-Neural-Networks-for-Emotion-Prediction Public

    Jupyter Notebook

  2. Cell-Lifelines-Autoencoder Cell-Lifelines-Autoencoder Public

    Jupyter Notebook

  3. Deep-Learning-in-Natural-Language-Processing-NLP- Deep-Learning-in-Natural-Language-Processing-NLP- Public

  4. Spotify-Song-Recommendation-System Spotify-Song-Recommendation-System Public

    Jupyter Notebook

  5. Probabilistic-Model-based-Machine-Learning-Reinforcement-Learning-on-CartPole Probabilistic-Model-based-Machine-Learning-Reinforcement-Learning-on-CartPole Public

    Jupyter Notebook

  6. Computational-Data-Analysis-Regression-Case Computational-Data-Analysis-Regression-Case Public

    Jupyter Notebook