https://github.com/alecruces/fashiondbn

Uncover the secrets of deep learning with FashionDBN - implementing PyTorch's Deep Belief Network for accurate image classification and beyond.
https://github.com/alecruces/fashiondbn

adversarial-attacks dbn image-classification

Last synced: 14 days ago
JSON representation

Uncover the secrets of deep learning with FashionDBN - implementing PyTorch's Deep Belief Network for accurate image classification and beyond.

• Host: GitHub
• URL: https://github.com/alecruces/fashiondbn
• Owner: alecruces
• Created: 2024-01-31T14:55:52.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-10T10:58:42.000Z (about 1 year ago)
• Last Synced: 2025-04-14T10:58:02.556Z (14 days ago)
• Topics: adversarial-attacks, dbn, image-classification
• Language: Jupyter Notebook
• Homepage:
• Size: 1.6 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Implementing a Deep Belief Network in PyTorch using the FashionMNIST dataset

---

##  Description 

The project focuses on the training of a Deep Belief Network using various hyperparameters such as hidden layers, nodes, and optimizer choices for optimizing performance in image classification. It analyzes the internal representations developed by the model through hierarchical clustering and feature visualization techniques. The goal is to understand the accuracy and psychometric curves for the DBN. Finally, it compares the ability of two models—the feedforward network and the DBN—to resist adversarial attacks.







##  Keywords

Image Classification, Deep Belief Network (DBN), FashionMNIST, Adversarial Attacks

##  Data 

* FashionMNIST dataset

## Methods  

* Deep Belief Network

* Feedforward networks

## Software 

* Python (Pytorch)

## Files  

* Code:

  - `code.ipynb`: Jupyter notebook that run al the project.

  - `DBN.py` and `RBN.py`: Have the functions called by `code.ipynb`.