About Me

Machine learning researcher with over 10+ years of experience in developing, evaluating, and deploying robust AI systems for complex, real-world data. Expertise spans neurotechnology, biosignals, multimodal learning, and foundational deep learning methods that ensure generalization and reliability in high-stakes applications.

My work emphasizes principled approaches to representation learning, domain adaptation, and rigorous model validation—rooted in deep expertise in signal processing and neural signal analysis, with strong foundational understanding of methods that underpin modern computer vision and large language models.

Research Interests

• Representation Learning and Generalization: Designing deep architectures (CNNs, Transformers, hybrids) for irregular, noisy, high-dimensional data; addressing distribution shifts through subject-independent and cross-domain methods.
• Biosignals and Neuro-AI: Advanced analysis of physiological signals (EEG, iEEG, ECG); brain-computer interfaces; feature engineering and time-series modeling with applications in healthcare and human-machine systems.
• Computer Vision and Multimodal AI: Vision Transformers, domain-invariant features, cross-modal integration; leveraging signal processing principles for robust image classification and adaptation.
• Large Language Models: Architectural innovations, fine-tuning techniques, and sequence modeling; applying LLMs to scientific data analysis, clinical decision support, and knowledge extraction.
• Evaluation and Research Methodology: Leakage-proof validation, statistical testing, ablation studies, and reproducible frameworks to build trustworthy AI systems.

Key Accomplishments

• IEEE Senior Member with publications in top-tier venues (IEEE Transactions, IEEE Access, peer-reviewed conferences).
• U.S. Patent 9,081,890: EEG-based rehabilitation training system, exemplifying end-to-end research-to-deployment.
• 1519+ citations (Google Scholar); h-index ~21, reflecting sustained impact in ML and neurotechnology.
• Open-source contributor: ML and signal processing toolkits on GitHub, promoting practical, reusable implementations.
• Technical educator: 3.1K+ YouTube subscribers, distilling complex ML and BCI concepts for broad audiences.
• Multidisciplinary leadership: Directed projects integrating engineering, clinical expertise, and industry needs.

Selected Publications

For a complete list, see Google Scholar.

• 2023: Abibullaev, B., Keutayeva, A., & Zollanvari, A. Deep Learning in BCIs: A Comprehensive Review of Transformer Models, Advantages, Challenges, and Applications. IEEE Access. [Link]
• 2022: Abibullaev, B., Kunanbayev, K., & Zollanvari, A. Subject-Independent Classification of P300 Event-Related Potentials Using a Small Number of Training Subjects. IEEE Transactions on Human-Machine Systems. [Link]
• 2021: Abibullaev, B. & Zollanvari, A. A Systematic Deep Learning Model Selection for P300-Based Brain-Computer Interfaces. IEEE Transactions on Systems, Man, and Cybernetics: Systems. [Link]
• 2019: Abibullaev, B. & Zollanvari, A. Learning Discriminative Spatiospectral Features of ERPs for Accurate Brain-Computer Interfaces. IEEE Journal of Biomedical and Health Informatics. [Link]

What I Offer

• Research-to-Production Expertise: Bridging theoretical ML advances with practical deployments, ensuring systems are robust, scalable, and ethically sound.
• Cross-Domain Insights: Applying core principles from signal processing to enhance vision, language, and multimodal models.
• Collaborative Innovation: Proven track record in high-stakes environments, from clinical trials to industrial prototypes.

Let’s Connect

Open to collaborations on AI research, model development, neurotechnology applications, or consulting on robust ML systems. Reach out to discuss ideas, share insights, or explore opportunities.

Explore my repositories, publications, and video lectures for more details.