This repository hosts both the first homework (NNDS_2024_Homework1) and the final project (NNDS_2024_Final_Homework.ipynb) for Neural Network for Data Science exam, held by Professor Simone Scardapane, as part of the Master’s degree in Data Science at Sapienza University of Rome.
The exam in Neural Network for Data Science consisted of one homework and a final project, plus and oral exam.
This repository details both the homework and the final project component of the course.
Directly from the course page here you can see the overview of the points assigned to each section of the exam (as of 2024):
For the final project, we were required to select our own dataset and build an autoregressive Recurrent Neural Network (RNN) fully in JAX, followed by providing examples of the sequences generated by the model.
You can find further details of the individual points to cover in the Final project notebook attached to this repository (NNDS_2024_Final_Homework.ipynb).
Both the first homework and the final project received a perfect score, 5 out of 5 for the homework and 10 out of 10 for the project. The overall score, including the oral exam, was 30/30, and the project was recognized as one of the best among all projects in the February exam session. Feel free to use it as a reference if you are planning to take the exam in the upcoming years.
Please do not hesitate to contact me if you need further explanations or encounter any issues with the materials.