Sapere Aude. "Dare to know." — Horace
温故知新 (Onko Chishin) "Cherishing old knowledge, acquiring new." — Japanese Idiom
I am a 4th-year Computer Engineering student at Manisa Celal Bayar University and a researcher in the field of Artificial Intelligence.
My academic focus is defined by a specific pursuit: bridging the gap between high-performance Deep Learning models and human cognitive understanding. I operate under the handle Aidoneus—a reference to the "Unseen"—reflecting my goal to make the hidden logic of "Black Box" algorithms visible and explainable.
My primary area of interest lies in Cognitive Game AI and Explainable AI (XAI). I am currently investigating how neural networks process strategic decisions in board games (specifically Go) and how these machine intuitions can be translated into human-readable concepts.
Key Methodologies:
- SHAP & LIME: Utilizing feature attribution methods to visualize move rationale.
- Deep Learning: Developing Convolutional Neural Networks (CNNs) for move prediction.
- Human-AI Collaboration: Enhancing the interpretability of AI agents for human learners.
1. Beyond the Move: Phase I Status: In Progress (Graduation Thesis) A Deep Learning framework designed to "Open the Black Box" of Go AI engines. This project implements SHAP and LIME values to visualize the rationale behind expert move generation, aiming to align AI decision-making with human intuition.
2. Gnothi Seauton (Γνῶθι σεαυτόν) Status: Continuous Integration A personal archive of technical exercises and algorithmic studies. This repository documents my continuous practice in Python, Data Structures, and Web Architecture.
I am open to academic collaboration and discussion regarding AI ethics and game strategy.
- ResearchGate: İpek Naz Sipahi
- Academic Mail: My mail
- LinkedIn: İpek Naz Sipahi
- Institution: Manisa Celal Bayar University, Türkiye
"The true sign of intelligence is not knowledge but imagination."