Skip to content
View HAYDARKILIC's full-sized avatar

Block or report HAYDARKILIC

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
HAYDARKILIC/README.md

Hi there, I'm HAYDAR KILIÇ 👋

Haydar's Profile Views

🔬 Research-Grade AI Engineering, Mathematical Foundations & Systems from Scratch

A researcher/engineer exploring the theoretical, mathematical, and infrastructural foundations of modern AI and Machine Learning by building them from scratch (pure NumPy, PyTorch & JAX). No high-level libraries; just pure math, algorithmic depth, and high-performance computing.


🛠️ Core Research & Repositories

🧠 Mechanistic Interpretability & Deep Learning

  • mechanistic_interpretability: Reverse-engineering neural network internals from scratch (NumPy + PyTorch). Linear representation hypothesis, superposition, SAEs, induction heads, and causal scrubbing.
  • deep_learning / derin_ogrenme: Everything about deep learning architecture and foundations.
  • geometric_deep_learning: Manifolds, equivariance, symmetry groups, GNNs, and Riemannian geometry.
  • graph_neural_networks: Spectral Graph Theory, graph Laplacian, over-smoothing, and raw GCN/GAT/GIN implementations.

📊 Mathematical Foundations (AI & ML)

⚡ Systems, Infrastructure & MLOps

  • distributed_systems_for_ml: Custom Ring All-Reduce primitives, Parameter Servers, 1F1B Pipeline Parallelism, and ZeRO/FSDP memory sharding from scratch.
  • high_performance_computing / hpc_ai_infra_llmops: Systems engineering required to train, fine-tune, and serve frontier-scale LLMs.
  • mlops_and_deployment: Custom experiment trackers, containerized model registries, dynamic batching inference servers, and high-performance LLM serving infra.
  • tensorlens: Visualizing Modern LLM Mechanics, Loss Landscapes & HPC Topologies.

🤖 Generative AI, Agents & Advanced NLP

🔮 Probabilistic ML & Advanced Estimation

⚛️ Quantum Artificial Intelligence & Computing

  • quantum_artificial_intelligence: Hands-on quantum computing for machine learning, built from scratch in NumPy then bridged to PennyLane. Covers qubits & gates, entanglement & CHSH, quantum algorithms (Deutsch–Jozsa, Grover, QFT), variational circuits & VQE, quantum ML classifiers, and quantum kernels.

👁️ Computer Vision & Advanced Image Processing


🚀 Tech Stack & Tools

  • Languages: Python, C++, CUDA
  • Math & Core ML: Pure NumPy, JAX, PyTorch, PennyLane, Numba
  • Systems & Operations: Distributed Training, HPC Topologies, MLOps, Triton/LLM Serving Infra

📨 Connect with me

"What I cannot create, I do not understand." — Richard Feynman

Popular repositories Loading

  1. uretken_yapay_zeka uretken_yapay_zeka Public

    İstatistiksel teoriden modern LLM'lere uzanan Üretken Yapay Zekâ masterclass'ı. Hazır framework'ler yok; saf matematik ve kodlama var. MAP/MLE türetimleri, VAE, GAN, Difüzyon süreçleri ve Attention…

    Jupyter Notebook 2

  2. veri_madenciligi veri_madenciligi Public

    Veri Madenciliği ve Makine Öğrenmesi için uygulamalı rehber. Temel ve ileri seviye sınıflandırma (KNN, Naive Bayes, YSA, SVM, Ansambl Yöntemleri), dengesiz veri yönetimi, Birliktelik Analizi (Aprio…

    Jupyter Notebook 1

  3. time_series_analysis time_series_analysis Public

    A comprehensive 10-lecture masterclass in Time Series Analysis and Forecasting. Covers stationarity, ARMA/SARIMA, Spectral Analysis, financial volatility (ARCH/GARCH), Multivariate VAR models, Coin…

    Jupyter Notebook 1

  4. deep_learning deep_learning Public

    Everything about deep learning

    Jupyter Notebook 1

  5. linear_algebra_for_ml linear_algebra_for_ml Public

    The linear algebra underpinning modern machine learning from scratch in pure NumPy then connects every construct back to the model that depends on it

    Jupyter Notebook 1

  6. Riemannian-Curve-Evolution Riemannian-Curve-Evolution Public

    Riemannian Curve Model Analysis: Image Segmentation Application