VS265: Syllabus - Revision history

Bruno at 07:14, 10 December 2014

2014-12-10T07:14:06Z

← Older revision		Revision as of 07:06, 10 December 2014
Line 84:		Line 84:
	* Limits of precision in neurons		* Limits of precision in neurons
	<!-- * Neural synchrony and phase-based coding -->		<!-- * Neural synchrony and phase-based coding -->

			==== Dec. 11: Guest lecture (Tony Bell) ====
			* Levels and loops

Bruno: /* Syllabus */

2014-12-10T07:13:08Z

Syllabus

← Older revision		Revision as of 07:05, 10 December 2014
Line 66:		Line 66:
	* Dynamical models		* Dynamical models

	==== Nov. 18,20,25: Probabilistic models and inference ====		==== Nov. 18,20,25, Dec. 2: Probabilistic models and inference ====

	* Probability theory and Bayes’ rule		* Probability theory and Bayes’ rule
Line 72:		Line 72:
	* The mixture of Gaussians model		* The mixture of Gaussians model
	* Boltzmann machines		* Boltzmann machines
	* Sparse coding and ‘ICA’
	* Kalman filter model		* Kalman filter model
	* Energy-based models		* Energy-based models

	==== Dec. 2,4: Neural implementations ====		==== Dec. 4: Guest lecture (Tony Bell) ====
			* Sparse coding and ‘ICA’

			==== Dec. 9: Neural implementations ====

	* Integrate-and-fire model		* Integrate-and-fire model
	* Neural encoding and decoding		* Neural encoding and decoding
	* Limits of precision in neurons		* Limits of precision in neurons
	* Neural synchrony and phase-based coding		<!-- * Neural synchrony and phase-based coding -->

	~~==== Dec. 9,11: Special topics ====~~

	* TBD
	* TBD

Bruno at 23:04, 4 November 2014

2014-11-04T23:04:14Z

← Older revision		Revision as of 22:56, 4 November 2014
Line 60:		Line 60:
	* Local linear embedding, Isomap		* Local linear embedding, Isomap

	==== Nov. 13~~,18~~: Recurrent networks ====		==== Nov. 13: Recurrent networks ====

	* Hopfield networks, memories as 'basis of attraction'		* Hopfield networks, memories as 'basis of attraction'
Line 66:		Line 66:
	* Dynamical models		* Dynamical models

	==== Nov. ~~13,~~18,20,25: Probabilistic models and inference ====		==== Nov. 18,20,25: Probabilistic models and inference ====

	* Probability theory and Bayes’ rule		* Probability theory and Bayes’ rule

Bruno: /* Oct. 30, Nov. 4,6: Recurrent networks */

2014-11-04T23:03:05Z

Oct. 30, Nov. 4,6: Recurrent networks

← Older revision		Revision as of 22:55, 4 November 2014
Line 60:		Line 60:
	* Local linear embedding, Isomap		* Local linear embedding, Isomap

	==== ~~Oct. 30,~~ Nov. 4,6: Recurrent networks ====		==== Nov. 13,18: Recurrent networks ====

	* Hopfield networks, memories as 'basis of attraction'		* Hopfield networks, memories as 'basis of attraction'

Bruno: /* Oct. 28: Manifold learning */

2014-11-04T23:02:34Z

Oct. 28: Manifold learning

← Older revision		Revision as of 22:54, 4 November 2014
Line 56:		Line 56:
	* Models of experience dependent learning and cortical reorganization		* Models of experience dependent learning and cortical reorganization

	==== ~~Oct~~. 28: Manifold learning ====		==== Nov. 6: Manifold learning ====

	* Local linear embedding, Isomap		* Local linear embedding, Isomap

Bruno: /* Oct. 23: Plasticity and cortical maps */

2014-11-04T23:01:59Z

Oct. 23: Plasticity and cortical maps

← Older revision		Revision as of 22:53, 4 November 2014
Line 50:		Line 50:
	* Projection pursuit		* Projection pursuit

	==== Oct. 23: Plasticity and cortical maps ====		==== Oct. 30, Nov. 4: Plasticity and cortical maps ====

	* Cortical maps		* Cortical maps

Bruno: /* Oct. 21: Sparse, distributed coding */

2014-11-04T23:01:06Z

Oct. 21: Sparse, distributed coding

← Older revision		Revision as of 22:53, 4 November 2014
Line 44:		Line 44:
	* Tom Dean, Google: Connectomics		* Tom Dean, Google: Connectomics

	==== Oct. 21: Sparse, distributed coding ====		==== Oct. 21,23,28: Sparse, distributed coding ====

	* Autoencoders		* Autoencoders

Bruno: /* Oct. 14: Unsupervised learning (continued) */

2014-10-14T19:25:10Z

Oct. 14: Unsupervised learning (continued)

← Older revision		Revision as of 19:17, 14 October 2014
Line 39:		Line 39:

	==== Oct. 14: Unsupervised learning (continued) ====		==== Oct. 14: Unsupervised learning (continued) ====

	* Linear Hebbian learning and PCA, decorrelation
	* Winner-take-all networks and clustering

	==== Oct. 16: Guest lecture ====		==== Oct. 16: Guest lecture ====

Bruno at 19:24, 14 October 2014

2014-10-14T19:24:41Z

← Older revision		Revision as of 19:16, 14 October 2014
Line 35:		Line 35:
	==== Oct. 7,9: Guest lectures ====		==== Oct. 7,9: Guest lectures ====

	* Jerry Feldman:		* Jerry Feldman: Ecological utility and the mythical neural code
	* Pentti Kanerva: Computing with 10,000 bits		* Pentti Kanerva: Computing with 10,000 bits

Bruno at 19:15, 14 October 2014

2014-10-14T19:15:33Z

← Older revision		Revision as of 19:07, 14 October 2014
Line 14:		Line 14:
	==== Sept. 9,11: Guest lectures ====		==== Sept. 9,11: Guest lectures ====

	* ~~TBD~~		* Matlab/Python tutorial
	* Paul Rhodes, Evolved Machines: Multi-compartment models; dendritic integration		* Paul Rhodes, Evolved Machines: Multi-compartment models; dendritic integration

Line 31:		Line 31:
	==== Sept. 30, Oct. 2: Guest lecture ====		==== Sept. 30, Oct. 2: Guest lecture ====

	* Fritz Sommer, Associative memories and attractor neural networks		* Fritz Sommer: Associative memories and attractor neural networks

	==== Oct. 2: Sparse, distributed coding ====		==== Oct. 7,9: Guest lectures ====

			* Jerry Feldman:
			* Pentti Kanerva: Computing with 10,000 bits

			==== Oct. 14: Unsupervised learning (continued) ====

			* Linear Hebbian learning and PCA, decorrelation
			* Winner-take-all networks and clustering

			==== Oct. 16: Guest lecture ====

			* Tom Dean, Google: Connectomics

			==== Oct. 21: Sparse, distributed coding ====

	* Autoencoders		* Autoencoders
Line 39:		Line 53:
	* Projection pursuit		* Projection pursuit

	==== Oct. 7: Plasticity and cortical maps ====		==== Oct. 23: Plasticity and cortical maps ====

	* Cortical maps		* Cortical maps
Line 45:		Line 59:
	* Models of experience dependent learning and cortical reorganization		* Models of experience dependent learning and cortical reorganization

	==== Oct. ~~9: Guest lecture ====~~		==== Oct. 28: Manifold learning ====

	* TBD

	~~==== Oct. 14~~: Manifold learning ====

	* Local linear embedding, Isomap		* Local linear embedding, Isomap

	==== Oct. 16: ~~Guest lecture~~ ====		==== Oct. 30, Nov. 4,6: Recurrent networks ====

	* Tom Dean, Google: Connectomics

	~~==== Oct. 21,23,28,30: Recurrent networks ====~~		* Hopfield networks, memories as 'basis of attraction'
	* Hopfield networks
	* Models of ~~associative memory, pattern completion~~
	* Line attractors and `bump circuits’		* Line attractors and `bump circuits’
	* Dynamical models		* Dynamical models

	==== Nov. ~~4,6,~~13,18,20,25: Probabilistic models and inference ====		==== Nov. 13,18,20,25: Probabilistic models and inference ====

	* Probability theory and Bayes’ rule		* Probability theory and Bayes’ rule
Line 80:		Line 86:
	* Neural synchrony and phase-based coding		* Neural synchrony and phase-based coding

	==== Dec. 9,11: ~~Guest lectures~~ ====		==== Dec. 9,11: Special topics ====

	* TBD		* TBD
	* TBD		* TBD