ECE 4001/7001 Neural Models and Machine Learning I (3 credits)

Course Description: Modeling neurons and networks as electrical circuits, machine learning in neuroscience, and usage of basic cyberinfrastructure tools. Extensive laboratory exercises focusing on (i) single cell and network models, including learning and behavior; (ii) design of related basic cyberinfrastructure tools.

Prerequisites: Calculus and linear systems, basic software programming, and basics of neurobiology or consent of instructor.

Instructor: Satish S. Nair, 229 EBW (882-2964;, with assistance from P Calyam Class Notes: These include course notes and software tutorials, which will be the basis for the laboratory exercise in the course. Numerous partly-developed CI tools will also be provided.

Detailed listing of topics:

  • Basic neurobiology, including modeling a neuron as an electrical circuit, including concepts of equilibrium points, stability and limit cycles
  • Basic of cyberinfrastructure tools relevant to neuroscience
  • Machine learning in neuroscience for big data applications
  • Extensive laboratory exercises in the development of single cell and network models using neurophysiology data. Students will be exposed to neural modeling packages including NEURON, and to basic cyberinfrastructure tools and their relevance in big-data neuroscience.
  • The lab exercises will emphasize software automation tools, including use of supercomputing facilities and cyberinfrastructure tools in neuroscience. This will familiarize students with these tools as well as provide opportunities to create their own interface tools, to address emerging needs of big data in neuroscience.

Grading: Laboratory Projects 60% Mid-term exam 15% Final Exam 25%

Letter grades: A > 90%; B 75-90%; C < 75% (ranges will be scaled depending on level of difficulty in exams)

Academic dishonesty: Academic honesty is fundamental to the activities and principles of a University. Any effort to gain an advantage not given to all students is dishonest whether or not the effort is successful. The academic community regards academic dishonesty as an extremely serious matter, with consequences that range from probation to expulsion. When in doubt about plagiarism, paraphrasing, quoting, or collaboration, consult the course instructor. If you are caught cheating on an exam or assignment, you will either receive a grade of zero for the exam/assignment, or an F for the course. Weekly assignments are individual assignments, so do not copy someone else's assignment. If you are caught committing academic dishonesty, your actions will be reported to the Provost's office, according to university policy.

Special needs: If you need accommodations because of a disability, if you have emergency medical information to share with me, or if you need special arrangements in case the building must be evacuated, please inform an instructor immediately. Please see an instructor privately after class, or during office hours. To request academic accommodations (e.g. a note-taker) students must register with Disability Services, AO38 Brady Commons, 882-4696. It is the campus office responsibility to review documentation provided by students requesting academic accommodations, and for accommodations planning in cooperation with students and instructors, as needed and consistent with course requirements.

Justification for graduate standing:The course is in a specialized area that is not part of the present undergraduate curriculum. It requires understanding introductory concepts in biology, calculus and programming. For the graduate section of the course, it will have both (i) advanced concepts in the topics covered (via additional readings), and (ii) development of more advanced computational neural projects.