Skip to content
View johnson70630's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report johnson70630

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
johnson70630/README.md

Hi 👋, I'm Johnson Chang

Taiwanese

  • 🔭 I’m currently pursuing Data Scientist / Machine Learning Engineer career

  • 🌱 I’m currently learning AI Models

  • 👨‍💻 All of my projects are available at My repositories

  • 💬 Ask me about :)

  • 📫 How to reach me [email protected]

  • ⚡ Fun fact I can fart with hands

Connect with me:

johnsonchang0_0 johnson chang https://leetcode.com/johnson70630/

Languages and Tools:

cplusplus git java mysql pandas python pytorch scikit_learn

 johnson70630

johnson70630

Pinned Loading

  1. Machine-Learning-from-Titanic-Disaster Public

    Build machine learning models to identify whether individuals on the Titanic survived for Kaggle competition (Titanic - Machine Learning from Disaster)

    Python 1

  2. Cryptocurrency-Trading-Strategy-Using-LSTM-for-Predicting-Profitable-Periods Public

    We are attempting to use LSTM models that handle time-series data to predict the periods when the strategy will be profitable or non profitable. By determining when to activate or deactivate the st…

    Jupyter Notebook 1

  3. GPT-Auto-Fine-Tuning-Line-Bot Public

    Fine-tuning GPT models can be quite challenging for the average user, requiring time to understand various concepts and some coding. The GPT Auto Fine-Tuning Line Bot simplifies this process by all…

    Python 1

  4. Addressing-Adversarial-Attacks-on-Computer-Images-Using-APE-GAN-and-Diffusion-Model Public

    In this project, we used Deepfool and FGSM to perform adversarial attacks on the MNIST dataset, reducing image recognition accuracy to 2% and 22%, respectively. Then, we used APE-GAN and the U-net …

    Jupyter Notebook 2

  5. Prompt-Engineering-for-Math-Problems Public

    As we known, LLMs are not good at inference, especially with mathematical problems. As a result, I researched on three prompt engineering methods and combined them to improve LLM on solving math pr…

    1

  6. Using-Multimodal-Model-AI-to-Develop-Stock-Trading-Strategy Public

    The project integrates sentiment and technical analysis using GNN, focusing on top 60 Taiwanese companies to predict stock movements. Data sources include news, stock charts, and macroeconomic indi…

    Jupyter Notebook 3