🧠 Deep Learning Projects

A curated collection of Deep Learning projects built using PyTorch, TensorFlow, Keras, and other popular deep learning frameworks.

This repository showcases practical implementations of Computer Vision (CNNs, Transfer Learning), Natural Language Processing (RNNs, LSTMs), Time Series Forecasting, Sentiment Analysis, and Medical Image Analysis.

Note: To keep the repository lightweight, large datasets, trained model weights (.pth, .pt, .h5, .keras), cache files, virtual environments, and generated outputs are excluded using .gitignore.

---

📁 Repository Structure

Deep-Learning-Projects/
│
├── Churn Prediction.ipynb
├── DogsVsCats.ipynb
├── Lung_Cancer_Detection_Using_Transfer_Learning.ipynb
├── Sentiment_Analysis.ipynb
├── Weather Forecasting.ipynb
├── cnn_fashion_mnist_pytorch_gpu.ipynb
├── lung-cancer-detection-using-cnn.ipynb
├── pytorch_lstm_next_word_prediction.ipynb
├── pytorch_rnn_based_qa_system.ipynb
├── sentiment_analysis_simplernn.ipynb
└── transfer_learning_fashion_mnist.ipynb

---

🚀 Projects Included

Project	Domain	Description
📉 Churn Prediction	ANN	Predict customer churn using an Artificial Neural Network.
🐶 Dogs vs Cats	CNN	Image classification of dogs and cats using Convolutional Neural Networks.
🫁 Lung Cancer Detection using Transfer Learning	Transfer Learning	Detect lung cancer from medical images using pretrained CNN models.
😊 Sentiment Analysis	NLP	Classify text sentiment using deep learning models.
🌦 Weather Forecasting	Time Series	Forecast future weather conditions using deep learning techniques.
👕 Fashion MNIST (PyTorch)	CNN	Train a CNN on the Fashion MNIST dataset using PyTorch.
🫁 Lung Cancer Detection using CNN	CNN	Detect lung cancer using a custom Convolutional Neural Network.
✍️ Next Word Prediction	LSTM	Predict the next word in a sentence using LSTM networks.
❓ RNN-based Question Answering	RNN	Build a simple Question Answering model using recurrent neural networks.
💬 Sentiment Analysis using SimpleRNN	SimpleRNN	Perform sentiment classification using a SimpleRNN architecture.
👔 Fashion MNIST Transfer Learning	Transfer Learning	Apply transfer learning techniques to the Fashion MNIST dataset.

---

🛠️ Technologies Used

• Python
• PyTorch
• TensorFlow
• Keras
• NumPy
• Pandas
• Matplotlib
• Scikit-learn
• OpenCV
• Jupyter Notebook

---

📚 Deep Learning Concepts Covered

Artificial Neural Networks (ANN)

• Feed Forward Neural Networks
• Binary Classification
• Multi-class Classification

Convolutional Neural Networks (CNN)

• Image Classification
• Medical Image Analysis
• Feature Extraction
• GPU Training

Transfer Learning

• Pretrained CNN Models
• Fine-Tuning
• Feature Extraction

Recurrent Neural Networks (RNN)

• Sequence Modeling
• Text Classification
• Question Answering

Long Short-Term Memory (LSTM)

• Next Word Prediction
• Language Modeling
• Sequential Data Processing

Natural Language Processing

• Tokenization
• Word Embeddings
• Padding
• Sentiment Analysis

Time Series Forecasting

• Sequential Data Prediction
• Forecast Modeling

---

📦 Repository Notes

To keep the repository lightweight and easy to clone, several files are intentionally excluded using the .gitignore file.

The following are typically not included:

• Large datasets
• Trained model weights (.pth, .pt, .h5, .keras)
• Serialized model files
• Python cache files (__pycache__/)
• Virtual environments (venv/, .venv/)
• TensorBoard logs
• Generated outputs
• IDE configuration files
• Temporary files

If you'd like to run any project locally, you may need to:

• Download the required dataset.
• Train the model to generate the saved weights.
• Update dataset paths if necessary.

---

▶️ Getting Started

1. Clone the repository

git clone https://github.com/<your-username>/Deep-Learning-Projects.git

2. Navigate to the repository

cd Deep-Learning-Projects

3. Install dependencies

pip install -r requirements.txt

If no requirements file is provided:

pip install torch torchvision tensorflow keras numpy pandas matplotlib scikit-learn opencv-python notebook

4. Launch Jupyter Notebook

jupyter notebook

Open any notebook and run the cells sequentially.

---

🎯 Skills Demonstrated

• Deep Learning Fundamentals
• Artificial Neural Networks
• Convolutional Neural Networks
• Transfer Learning
• Recurrent Neural Networks
• Long Short-Term Memory Networks
• Natural Language Processing
• Image Classification
• Medical Image Analysis
• Time Series Forecasting
• Model Evaluation
• GPU Training
• Data Visualization
• PyTorch
• TensorFlow
• Keras

---

📈 Learning Outcomes

This repository demonstrates hands-on experience with:

• Binary & Multi-class Classification
• Image Processing
• Feature Extraction
• Sequence Modeling
• Text Generation
• Sentiment Analysis
• Transfer Learning
• Medical AI Applications
• Time Series Prediction
• Building Deep Learning Pipelines

---

🔮 Future Enhancements

• Vision Transformers (ViT)
• BERT & Transformer Models
• Object Detection (YOLO)
• Image Segmentation (U-Net)
• GANs (Generative Adversarial Networks)
• Autoencoders
• Attention Mechanisms
• Hugging Face Transformers
• MLOps for Deep Learning
• Model Deployment using Streamlit/FastAPI

---

🤝 Contributing

Contributions are welcome!

1. Fork this repository.
2. Create a new feature branch.
3. Commit your changes.
4. Push to your fork.
5. Open a Pull Request.

---

⭐ Show Your Support

If you found this repository useful, consider giving it a ⭐ on GitHub.

---

👨‍💻 Author

Jeremiah Ranen

• GitHub: https://github.com/jeremiahranen7
• LinkedIn: https://www.linkedin.com/in/jeremiahranen/