Welcome to the Lecture Examples repository! This repository contains Python code files used as examples during my lectures. Each lecture is organized into a separate folder for easy navigation and reference.
- Lecture 1: Machine learning overview and classical regression
- Lecture 2: Neural networks for regression and classification
- Lecture 3: Unsupervised Learning
- Lecture 4: Hybrid models and physics-Informed neural networks
- Lecture 5: Computer vision
- Lecture 6: Molecular property prediction with graph neural networks
- Lecture 7: ChatGPT and ethical aspects in AI
Each lecture is organized into a separate folder with a meaningful name to help you quickly find the relevant code examples. Inside each folder, you'll find Python code files (.ipynb) and any additional resources or documentation related to the lecture.
lecture_1/
├── Lecture1.example.py
├── ...
├── README.md (Optional: Additional information about Lecture 1)
You can also run the code online via Google's Colaboratory. Colab allows users with Google accounts to execute Jupyter notebooks on the Google cloud.
To execute the notebook in Colab:
- Click the
Open in Colab
button above. It will launch the notebook directly. - Make the notebook live by clicking 'Connect' in the Colab toolbar.
- Select
Runtime > Run All
in the menu to execute the notebook. (You may get a warning that the page was not authored by Google.)
-
Clone this repository to your local machine:
git clone https://github.com/your-username/lecture-examples.git
-
Navigate to the specific lecture folder you are interested in.
-
Explore the Python code files provided as examples during the lecture.
Feel free to use these code examples for reference or in your own learning journey. If you have any questions or need further explanations, please don't hesitate to reach out.
This repository is open-source and available under the MIT License. Feel free to use, modify, and distribute the code examples as needed.