Gradient Descent¶
Source folder: Gradient-Descent/
Summary¶
Homework project focused on understanding gradient descent behavior through custom objective functions and visual experimentation.
Analysis Used¶
- Construction of scalar objective functions and analytical derivatives.
- Step-by-step 1D gradient descent implementation and testing.
- Experiments with learning-rate and initialization choices.
- Extension to higher-dimensional gradients and contour analysis.
- Visual interpretation of convergence versus oscillation/divergence.
Technologies and Methods¶
- Python, Jupyter Notebook
numpyplotly.graph_objectsIPython.display