Harvard Canvas Site [login required]
Homework, Project Timeline and Credits
IMPORTANT ANNOUNCEMENTS:
First class: Tuesday January 28th, 2025. 3pm.
Please fill in this survey before class starts
This is a seminar-style course which provides a foundational overview of key ideas in Computational Neuroscience and the study of Biological Intelligence. At the same time, the course will connect the study of brains to the blossoming and rapid development of ideas in Artificial Intelligence. Topics covered include the biophysics of computation, neural networks, machine learning, bayesian models, theory of learning, deep convolutional networks, generative adversarial networks, neural coding, control and dynamics of neural activity, applications to brain-machine interfaces, connectomics, among others. Lectures will be taught by leading Harvard experts in the field.
Faculty include: Andrei Barbu, Richard Born, Jan Drugowitsch, Isaac Kohane, Gabriel Kreiman, Bill Lotter, Cengiz Pehlevan, Kanaka Rajan, Thomas Serre, Haim Sompolinsky, Cass Sunstein, Tomer Ullman
Course Meeting Times and Schedule
Tuesdays 3:00 pm to 5:00 pm
> Additional tutorial sessions will be announced soon
Location: Northwest Building B101
There won’t be an official book for the class. Here are some interesting books that touch upon some of the topics covered in class.
• Kreiman G (2021). Biological and Computer Vision. Cambridge University Press.
• Ullman S (1996) High-level vision. MIT Press.
• Ripley. Pattern recognition and neural networks (1996). Cambridge University Press.
• Rao, Olshausen and Lewicki (eds) (2002). Probabilistic models of the brain. MIT Press.
• Koch C (2005) The quest for consciousness. Roberts & Company Publishers.
• Dayan and Abbott (2002). Theoretical Neuroscience. MIT Press.
• Davies ER. (2005). Machine Vision, Third Edition: Theory, Algorithms, Practicalities (Signal Processing and its Applications). Elsevier.
• Sutton RS, Barto AG. (2018) Reinforcement Learning: An Introduction. MIT Press
• Vapnik, V. (1998). The Nature of Statistical Learning Theory. Springer.
• Poole D, Mackworth, A. (2017) Artificial Intelligence: foundations of computational agents, 2nd edition, Cambridge University Press.
• Goodfellow I, Bengio Y, Courville A. (2016) Deep learning. MIT Press.
• Poggio TA, Anselmi F. Visual Cortex and Deep Networks (2016). Learning Invariant Representations. MIT Press.
Collaboration Policy Statement
Discussion with other students and with people outside the class is permitted throughout the course. Students can also utilize any relevant material from the library or the web. Students must adequately cite any material that they use.
Each student must work on his/her own project. No two projects can be identical. There can be no group projects. All work should be entirely the student's own work. The use of textbooks, books, articles, and web resources is encouraged.
The final write-up has to be exclusively the work of the student. If material is reported from other sources, it should be reported as a quote and cited. Projects involving code and algorithms can use existing code from public repositories. Any such code should be adequately cited. All code used in any models or simulations should be turned in accompanying the final report.
Teaching Assistants
Dianna Hidalgo: diannahidalgo@g.harvard.edu
Valerio Pepe: valeriopepe@college.harvard.edu
Purab Seth: purabseth@college.harvard.edu
Office hours:
Gabriel Kreiman:
Tuesdays, 11am-12pm ET
Zoon only: https://harvard.zoom.us/j/8438302804
Please click here to book appointmentDianna Hidalgo:
Tuesdays 1:30pm - 2:30pm
Location: Northwest 243
Valerio Pepe
Wednesdays 4-5 PM.
Location: Northwest 243
Purab Seth
Wednesdays TBD.
Location: TBD
