🚧 WARNING: UNDER CONSTRUCTION 🚧

⚠️ VISITOR WARNING ⚠️
The repositories below are primarily academic artifacts.
They are incomplete, unmaintained, and held together by duct tape and student tears.
Do not expect production code. Expect "it worked on my machine 5 minutes before the deadline" code.

---

👋 Hi, I’m Nathan

I am navigating the messiness of real-world data and the abstract theory of deep learning.

🎓 Data Science Student @ The Hebrew University of Jerusalem
🔬 Research Data Scientist @ Israel Central Bureau of Statistics (CBS) (Specifically the Statistical Methodology Department, where I research Deep learning and Explainable AI (xAI) for national data)

🔭 Current Focus

My academic focus has shifted from standard ML & stats to Generative Models, Deep Learning, Computer Graphics, and Image Processing. I am currently breaking things in:

• Deep Generative Models: Diffusion, GANs, and Autoencoders.
• Image Processing & Computer Graphics: 3D vision concepts and heavy image processing pipelines.
• xAI Research: Trying to make black-box models explain themselves in a government context mathematically.

---

🚧 Active Construction Zones (Newer Coursework)

These projects are currently being built (or broken) as part of my advanced electives.

• Generative Models: Exploring Diffusion Models, VAEs, and GAN architectures.
• Image Processing: Low-level vision, filtering, and frequency domain manipulation.
• Computer Graphics: 3D rendering pipelines, geometry processing, and ray tracing.

🏛️ The Graveyard (Past Academic Repositories)

Most of these are frozen in time. They served their purpose for a grade and have been abandoned since.

Deep Learning & Neural Networks

• Intro to Deep Learning (67822): My sandbox for PyTorch implementations. Contains custom Convolutional Autoencoders (CAEs), Transfer Learning experiments, and from-scratch implementations of RNNs and Attention mechanisms.

Statistical Foundations

• Regression & Models (52571): Heavy focus on GLMs and theoretical constraints.
• Statistical Learning (52525): The mathematical backbone of my ML knowledge.
• Big Data Mining (52002): Handling data at scale (or trying to).

---

🛠️ The Toolkit

• Languages: Python (Native), SQL (Fluent), Bash (Love it), C/C++ (where i started - Native)
• Frameworks: PyTorch (Daily driver), scikit-learn, pandas, NumPy, MatPlotLib
• Infrastructure: Docker, FastAPI, Redis
• Tools: JupyterLab, Git

🤝 Collaborative Interests

If you are okay with experimental code, I am open to:

• Deep learning research (specifically PyTorch/Transformers)
• Architectural innovation in Neural Networks
• Applied ML pipelines that need to scale

I'm really busy right now finishing my degree...

⚡ Fun Fact

I play guitar and listen to Heavy Metal. Much like the current GitHub state, it is loud, complex, and sometimes difficult to understand.