Skip to content

Latest commit

 

History

History
33 lines (23 loc) · 1.4 KB

README.md

File metadata and controls

33 lines (23 loc) · 1.4 KB
Raw

HUPLACLIP-NNs

This repository evaluates the performance of various AI models on the Planted Clique Problem, a theoretical computer science task focused on detecting hidden cliques within graphs.

Repository Structure

  • main.py: Main script for running experiments.
  • README.md: Project documentation.
  • requirements.txt: Lists the necessary Python packages and dependencies on personal laptop.
  • requirements_Leo.txt: Lists the necessary Python packages and dependencies Leonardo HPC cluster.
  • .gitignore: Specifies files and directories to be ignored by Git.

Folders

  • docs/: Contains documentation files.
    • grid_exp_config.yml: Specifies all experiment parameters, such as model types, hyperparameters, and graph settings.
  • results/: Directory where experiment results are saved.
  • scripts/: Additional scripts for setup, preprocessing, or visualizations.
  • src/: Source files that include modules for data generation, model definitions, and training functions.
  • tests/: Contains unit tests for the various functions and modules in the project.

Models

The AI models tested include:

  • MLP (Multi-Layer Perceptron)
  • CNN (Convolutional Neural Network)
  • ViT (Vision Transformer)

Contact

For inquiries, please contact:
Daniele Tirinnanzi - daniele.tirinnanzi@unicampus.it