Computational Neuroscience and Neural Networks

NEU 385L / EE 385V / PHY 392T
Spring 2017
The University of Texas at Austin
 
location: GDC 1.406
time: Friday 12:00-3:00 pm
 
instructor: Professor Ila Fiete (fiete [at] mail.clm.utexas.edu)
teaching assistant: Tzuhsuan (Maz) Ma (tzuhsuan [at] physics.utexas.edu)

office hours:
Dr. Fiete: Fri 11-noon (NHB 3.354) and by appt.
Maz: TBA (NHB 3.350) and by appt.
 
syllabus: PDF
textbook: Theoretical Neuroscience by Dayan and Abbott 2001; also available on Amazon.
other useful books: Pattern Recognition and Machine Learning by Christopher Bishop; see bottom of this page for many more reading recommendations.
course schedule
DateTopic Reading Homework
Fri 1.20 Introduction to course aims. Notation. Neurons, spikes, rates.
Fri 1.27 UNIT 1: MEMORY, RECURRENT NETWORKS, INTEGRATORS.
Fri 2.03
Fri 2.10
Fri 2.17
Fri 2.24
Fri 3.03 UNIT II: (UNSUPERVISED, REINFORCEMENT, SUPERVISED) LEARNING, FEEDFORWARD NETWORKS
Fri 3.10
Fri 3.17
Fri 3.24
Fri 3.31
Fri 4.07 UNIT III: SENSORY SYSTEMS; RESEARCH FRONTIERS; STUDENT CHOICE; PROJECTS
Fri 4.14
Fri 4.21
Fri 4.28
Fri 5.05
 
further reading:
  If you leave this class with a bigger appetite for theoretical/computational neuroscience, there are a number of next steps. I recommend Spikes (Rieke et al.; a monograph on information in neural activity and codes), Biophysics of Computation (Koch; a monograph focused on single-neuron biophysics), and Analysis of Neural Data (by Brown; the title says it all -- statistical analysis of neural data). These are generally upper-division undergraduate/graduate texts. For learning theory, try reading Learning from data (Abu-Mostafa et al.). For deep learning/training neural networks, see Deep Learning (Goodfellow et al.) and visit the following website for a vast list of resources including links to online courses, books, lectures, datasets, and tutorials.
 
 

page maintained by Ila Fiete and Kijung Yoon