Teaching
I have designed and delivered courses in the Robotics & Mechatronics program at Nazarbayev University (2015–present), emphasizing active, hands-on learning with real-world applications in signals, machine learning, neural interfaces, and embedded systems. My courses feature Python/PyTorch/MNE-Python implementations, hardware labs (OpenBCI, FPGA, microcontrollers), and research-integrated projects — many resulting in student IEEE publications.
For full syllabi, lecture notes, project examples, and code repos: 👉 Complete Courses Overview → brainu.notion.site
YouTube Channel
@berdakh-abibullaev · 3,100+ subscribers · 59+ videos
Open lecture recordings, tutorials, and practical demos covering neurotech, BCI, EEG analysis, and ML tools — serving as open educational resources for students, researchers, and self-learners worldwide.
Courses
ROBT 206: Microcontrollers with Lab
Core Undergraduate · Robotics & Mechatronics Program
Covers Boolean algebra, logic and circuit design, instruction sets, and microcontroller peripherals and programming. Tools include Arduino IDE, MATLAB, Quartus, and Proteus for circuit simulation. Labs involve hands-on FPGA board programming and electronic component work, with emphasis on practical digital system design and embedded programming skills.
ROBT 407: Machine Learning with Applications
Undergraduate/Graduate Elective · 40–60 students/year
PyTorch-based course using real datasets (neural signals, sensors, biomedical measurements), with emphasis on implementation, model interpretability, and ethical AI. Student projects have resulted in 15+ IEEE conference papers and 3+ peer-reviewed journal publications.
👉 Complete ML Course Playlist → YouTube
Signals and Systems
Core Undergraduate · 40+ students/year
Modernized with Python simulations and real-world biomedical labs (ECG/EEG, industrial signals). Course opens with clinical problems (e.g., ECG arrhythmia detection) to motivate theory before formalism.
Brain-Machine Interfaces / Brain-Computer Interfaces
Graduate Capstone Seminar
Hands-on lab course covering the full BCI pipeline: acquisition → preprocessing → feature extraction → real-time decoding. Hardware: OpenBCI and EEG amplifiers. Software: MNE-Python, scikit-learn, PyTorch. Outcomes include 20+ student-led IEEE publications (EMBC, BCI, NER).
👉 BCI Lectures → YouTube · MNE-Python Tutorials → YouTube
Statistical Methods and Machine Learning
Undergraduate Foundation · 2015–2020 · 40+ students/year
Foundational statistics combined with applied ML (scikit-learn), with Jupyter tutorials and peer-review exercises for interactive learning.
Teaching Preparation
Graduate training at Yeungnam University (M.S. 2004–2006; Ph.D. 2006–2010) included advanced coursework in signal processing, systems theory, digital and VLSI design, control, and biomedical engineering. Combined with 10+ years of faculty experience, this provides a broad foundation for teaching core and specialized topics across the following areas:
Signal Processing & Biomedical Signals — Bio-signal processing, random signal processing, digital image processing, multimedia signal processing.
Digital Design, Circuits & Embedded Systems — Digital logic design, HDL, electronic circuits, microprocessor-based systems, VLSI system design, semiconductor devices.
Machine Learning, AI & Data-Driven Methods — Neural networks, deep learning, supervised and unsupervised methods, model selection, interpretability.
Biomedical & Neural Engineering — Biomedical measurement, bioelectronic engineering, brain-computer interfaces.
Potential electives — Computer Vision, Data Science, AI for Medical Devices, Cyber-Physical Systems.
Approach: Active, project-based learning with real datasets and hardware; research integration (current transformer and BCI results used in lectures); inclusive design with multiple modalities, scaffolding, and formative feedback; emphasis on ethical AI, interpretability, and professional skills. Student outcomes include 30+ publications from course projects.