• Concepts
• NTU Courses
• Linear Algebra
• Keras
• scikit-learn

Concepts¶

• MCP (Model Context Protocol)
• connecting AI applications to external systems

• https://modelcontextprotocol.io/docs/getting-started/intro

• Harness Agent = for long, multi-step tasks

• https://learn.microsoft.com/en-us/agent-framework/overview/?pivots=programming-language-python
• https://learn.microsoft.com/en-us/agent-framework/concepts/harness?pivots=programming-language-python

NTU Courses¶

• 2014-2021: http://speech.ee.ntu.edu.tw/~tlkagk/courses.html
• 2023/2025: https://csdiy.wiki/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/LHY/
• https://www.youtube.com/watch?v=fegAeph9UaA&index=3&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49

Linear Algebra¶

http://speech.ee.ntu.edu.tw/~tlkagk/courses_LA16.html

Keras¶

deep learning API written in Python and capable of running on top of either JAX, TensorFlow, or PyTorch. - https://keras.io/getting_started/about/ - NTU LHY: https://www.youtube.com/watch?v=Lx3l4lOrquw&list=PLJV_el3uVTsPy9oCRY30oBPNLCo89yu49&index=13

scikit-learn¶

works natively with tabular data like pandas DataFrames - Examples: https://scikit-learn.org/stable/auto_examples/index.html

PyCon TW 2016: https://www.slideshare.net/aacs0130/scikitlearn-62706630