Artificial intelligence in neuroscience is no longer an emerging curiosity. It is an active clinical frontier reshaping how brain disorders are detected, monitored, and managed. For clinicians working in functional neurology and related disciplines, understanding how machine learning, deep learning, convolutional neural networks, and large language models intersect with neuroimaging and neurological assessment is becoming foundational to advanced practice. This course provides that foundation with precision, depth, and clinical relevance.

‍

The course examines the full landscape of AI methodologies as they apply to neuroscience data, including supervised and unsupervised learning, transformer architectures, generative AI, and self-supervised learning frameworks. Clinicians gain the conceptual fluency to understand how these tools process EEG, fMRI, MRI, genetic, and clinical note data simultaneously, moving beyond single-modality interpretation toward integrated, multimodal diagnostic intelligence. Real-world case examples from brain tumor classification, extracapsular extension detection in oncology imaging, and automated radiology reporting ground these concepts in applied clinical contexts.

‍

This course is designed for licensed clinicians with a serious interest in how computational neuroscience tools are changing what is possible in assessment and care. No prior programming knowledge is required. What is required is an appetite for understanding the next generation of clinical decision support and the intellectual framework to evaluate it critically.

‍

Instructor Pegah Khosravi leads the BioMind AI Lab and brings direct research experience from Memorial Sloan Kettering Cancer Center and Weill Cornell Medical College. Her published work spans lightweight CNN architecture development, explainable AI, transfer learning for clinical imaging, and AI ethics in medical data. She brings research-grade expertise directly into the clinical education space.