I design and deliver end-to-end machine learning systems—from problem framing and data strategy to reliable deployment and lifecycle management. My work blends applied research with production engineering, emphasizing clarity, scalability, and measurable impact.
I focus on generalizable capabilities rather than tool-of-the-month specifics: Computer Vision, NLP & LLMs, Biomedical AI, Generative AI, Representation Learning, Optimization & AutoML, and MLOps.
My approach centers on reproducibility, operational excellence, and responsible AI.
- 🎓 MSc. in progress (Machine Learning / Deep Learning)
- 🧪 Research orientation with practical delivery across multiple domains
- 🛠️ Reproducible workflows (configuration, tracking, evaluation, CI/CD, containers)
|
|
|
|
|
|
|
|
|
|
|
|
- 📄 ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation
- 📄 Synthetic ALS-EEG Data Augmentation for ALS Diagnosis Using Conditional WGAN with Weight Clipping
- 📄 Novel Performance-Based Hyperparameter Optimization with the Use of Bounding Box Tuner (BBT)
- 📄 Artificial Intelligence in Electroencephalography: A Comprehensive Survey of Methods, Challenges, and Applications
|
|
|
|
- Outcome-oriented: clear goals, measurable impact
- Reproducible by default: deterministic pipelines, configs, experiment tracking
- Operational excellence: monitoring, CI/CD, resilient systems
- Responsible AI: fairness, safety, privacy-aware design
- Simplicity first: maintainable abstractions, progressive refinement
- Collaboration: docs, reviews, mentorship
📧 [email protected] · 🌐 abdulvahapmutlu.com · 💼 LinkedIn
