Skip to content

dae9999nam/deep_learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

Research Project

Python PyTorch Jupyter

Personal deep learning study and research notes, organized for experimentation, review, and long-term reuse.

Overview

This repository is a personal workspace for self-directed deep learning study and research. It is intended to keep experiments, learning notes, implementation practice, and research references organized in one place.

Purpose

  • Build a deeper understanding of deep learning by implementing and testing ideas directly.
  • Track lectures, papers, tutorials, and coding experiments in a single repository.
  • Keep experiments and observations in a reproducible, reviewable format.
  • Separate study notes from research notes as the project grows.

Current Structure

research_proj/
└── deep_learning/
    ├── CNN.ipynb
    └── MLP.ipynb

What This Repository Contains

  • deep_learning/CNN.ipynb: notes and experiments related to convolutional neural networks.
  • deep_learning/MLP.ipynb: notes and experiments related to multilayer perceptrons.

Working Principles

  • Keep notebooks focused on a single topic or experiment.
  • Record the goal, core idea, results, and follow-up questions together.
  • Prefer code that is easy to rerun and results that are easy to reproduce.
  • Avoid committing large datasets, temporary files, or generated artifacts.

Recommended Organization

As the repository expands, a structure like the following will help keep it maintainable:

research_proj/
├── deep_learning/
├── notes/
├── experiments/
└── references/

File Exclusions

Based on the current .gitignore, the repository excludes:

  • PDF documents
  • CSV files
  • Excel spreadsheets
  • Word documents
  • macOS metadata files

Suggested Workflow

  1. Choose a topic or research question.
  2. Create or update the relevant notebook under deep_learning/.
  3. Document the experiment setup, key results, and interpretation in the notebook.
  4. Keep the work reproducible by recording important parameters and assumptions.
  5. Move broader summaries or references into dedicated folders as the repository grows.

License

This repository is currently for personal learning and research. Add a license later if you plan to share or publish the work.

About

This repository is a personal workspace for self-directed deep learning study and research. It is intended to keep experiments, learning notes, implementation practice, and research references organized in one place.

Topics

Resources

Stars

Watchers

Forks

Contributors