TUTORIALS

Video lectures and supporting materials introduce many advanced modeling and data analysis methods used in intelligence research that integrates computational and empirical approaches.

Feedback on the Learning Hub

LH - -Computational Tutorial: Learning in Recurrent Neural Networks

Learning in Recurrent Neural Networks

Learning in Recurrent Neural Networks

MIT, Columbia

Introduction to recurrent neural networks and their application to modeling and understanding real neural circuits.

Taught by: Larry Abbott, Columbia University

Video:

Learning in recurrent neural networks (1:16:39)

Slides:

Learning in recurrent neural networks

Additional Resources:

Notes on Boerlin, Machens and Deneve (learning in recurrent spiking network) - Larry Abbott's notes
Exercises
Recursive Least-Squares Algorithm - Larry Abbott's notes
Sompolinsky, H., Crisanti, A. & Sommers, H. J. (1988) Chaos in random neural networks, Physical Review Letters 61:259.
Rajan, K., Abbott, L. F. & Sompolinsky, H. (2010) Stimulus-dependent suppression of chaos in recurrent neural networks, Physical Review E 82:011903.
Sussillo, D. & Abbott, L. F. (2009) Generating coherent patterns of activity from chaotic neural networks, Neuron 63:544-557.
Boerlin, M., Machens, C. K. & Deneve, S. (2013) Predictive coding of dynamic variables in balanced spiking networks, PLoS Computational Biology 9:e1003258.