Machine Learning Researcher
Building stable & interpretable AI systems for real-world applications
Specializing in computer vision, NLP, and generative AI with focus on accessibility and healthcare.
Building stable & interpretable AI systems for real-world applications
Specializing in computer vision, NLP, and generative AI with focus on accessibility and healthcare.
I'm a Machine Learning Researcher focused on building stable and interpretable AI systems that perform reliably with noisy real-world data. My approach emphasizes multi-stage pipelines that separate detection, alignment, refinement, and decoding instead of relying on black-box end-to-end models.
My research spans computer vision, natural language processing, and generative AI, with particular interest in accessibility technology and healthcare applications. I've contributed to multiple research projects resulting in manuscripts currently under review in computer vision and NLP domains.
With hands-on experience across the full ML pipeline from data collection and annotation to model training, evaluation, and deployment I bring both technical depth and practical execution capabilities to research projects.
Multi-stage pipeline for Braille recognition using YOLOv11, PCA deskewing, and attention-based CNN with transformer correction. Achieved 9.7% CER and eliminated silent decoding failures.
Manuscript Under Review View DetailsHybrid evolutionary-adversarial model combining YOLO detection, PSO/CMA-ES refinement, and dual-GAN architecture for realistic handwriting generation.
Manuscript Under Review View DetailsAdvanced Intrusion Detection System for Industrial IoT using LSTM, TCN-Attention, and CNN-LSTM models with flow-based splitting. Achieved 99.99% accuracy.
Completed View Details