How pabair/ml2-ws26 works
This repository is course material for “Maschinelles Lernen 2,” organized as three numbered learning notebooks and two corresponding solution notebooks. The filenames indicate a progression from NumPy basics to digit classification with logistic regression and neural networks implemented in NumPy. The README documents the course and a Jupyter-based environment, but no notebook contents were provided, so internal calls, datasets, and notebook-to-notebook dependencies cannot be verified. Learner-to-notebook links are therefore shown as unverified.
Main entry points: 00_Numpy_Tutorial.ipynb NumPy tutorial · 01_Digits_with_LogReg.ipynb Digits logistic regression · 02_NeuralNets_Numpy.ipynb NumPy neural networks · 01_Digits_with_LogReg-Solution.ipynb Logistic regression solution
Components 6
Course notebooks
- NumPy tutorial
00_Numpy_Tutorial.ipynb - Digits logistic regression
01_Digits_with_LogReg.ipynb - NumPy neural networks
02_NeuralNets_Numpy.ipynb
Worked solutions
- Logistic regression solution
solutions/01_Digits_with_LogReg-Solution.ipynb - Neural networks solution
solutions/02_NeuralNets_Numpy-Solution.ipynb
Other components
- Learner
Connections 5
- Learner → NumPy tutorial: studies
- Learner → Digits logistic regression: studies
- Learner → NumPy neural networks: studies
- Learner → Logistic regression solution: reviews
- Learner → Neural networks solution: reviews