HOME MISSION AND RESEARCH PUBLICATIONS HISTORY PEOPLE SEMINARS COURSES VIDEO ARCHIVE CONTACT

Difference between revisions of "VS265: Syllabus"

From RedwoodCenter

(Oct. 14: Manifold learning)
(Syllabus)
Line 2: Line 2:
  
 
==== Aug. 28: Introduction ====
 
==== Aug. 28: Introduction ====
# Theory and modeling in neuroscience
+
* Theory and modeling in neuroscience
# Goals of AI/machine learning vs. theoretical neuroscience
+
* Goals of AI/machine learning vs. theoretical neuroscience
# Turing vs. neural computation
+
* Turing vs. neural computation
  
 
==== Sept. 2,4: Neuron models ====
 
==== Sept. 2,4: Neuron models ====
  
# Membrane equation, compartmental model of a neuron
+
* Membrane equation, compartmental model of a neuron
# Linear systems: vectors, matrices, linear neuron models
+
* Linear systems: vectors, matrices, linear neuron models
# Perceptron model and linear separability
+
* Perceptron model and linear separability
  
 
==== Sept. 9,11: Guest lectures ====
 
==== Sept. 9,11: Guest lectures ====
  
# TBD
+
* TBD
# Paul Rhodes, Evolved Machines:  Multi-compartment models; dendritic integration
+
* Paul Rhodes, Evolved Machines:  Multi-compartment models; dendritic integration
  
 
==== Sept. 16,18: Supervised learning ====
 
==== Sept. 16,18: Supervised learning ====
  
# Perceptron learning rule
+
* Perceptron learning rule
# Adaptation in linear neurons, Widrow-Hoff rule
+
* Adaptation in linear neurons, Widrow-Hoff rule
# Objective functions and gradient descent
+
* Objective functions and gradient descent
# Multilayer networks and backpropagation
+
* Multilayer networks and backpropagation
  
 
==== Sept. 23,25: Unsupervised learning ====
 
==== Sept. 23,25: Unsupervised learning ====
  
# Linear Hebbian learning and PCA, decorrelation
+
* Linear Hebbian learning and PCA, decorrelation
# Winner-take-all networks and clustering
+
* Winner-take-all networks and clustering
  
 
==== Sept. 30:  Guest lecture ====
 
==== Sept. 30:  Guest lecture ====
  
# TBD
+
* TBD
  
 
==== Oct. 2:  Sparse, distributed coding ====
 
==== Oct. 2:  Sparse, distributed coding ====
  
# Autoencoders
+
* Autoencoders
# Natural image statistics
+
* Natural image statistics
# Projection pursuit
+
* Projection pursuit
  
 
==== Oct. 7:  Plasticity and cortical maps ====
 
==== Oct. 7:  Plasticity and cortical maps ====
  
# Cortical maps
+
* Cortical maps
# Self-organizing maps, Kohonen nets
+
* Self-organizing maps, Kohonen nets
# Models of experience dependent learning and cortical reorganization
+
* Models of experience dependent learning and cortical reorganization
  
 
==== Oct. 9:  Guest lecture ====
 
==== Oct. 9:  Guest lecture ====
  
# TBD
+
* TBD
  
 
==== Oct. 14:  Manifold learning ====
 
==== Oct. 14:  Manifold learning ====
  
# Local linear embedding, Isomap
+
* Local linear embedding, Isomap
  
 
==== Oct. 16:  Guest lecture ====
 
==== Oct. 16:  Guest lecture ====
  
# Tom Dean, Google:  Connectomics
+
* Tom Dean, Google:  Connectomics
  
 
==== Oct. 21,23,28,30:  Recurrent networks ====
 
==== Oct. 21,23,28,30:  Recurrent networks ====
# Hopfield networks
+
* Hopfield networks
# Models of associative memory, pattern completion
+
* 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. 4,6,13,18,20,25:  Probabilistic models and inference ====
  
# Probability theory and Bayes’ rule
+
* Probability theory and Bayes’ rule
# Learning and inference in generative models
+
* Learning and inference in generative models
# The mixture of Gaussians model
+
* The mixture of Gaussians model
# Boltzmann machines
+
* Boltzmann machines
# Sparse coding and ‘ICA’
+
* Sparse coding and ‘ICA’
# Kalman filter model
+
* Kalman filter model
# Energy-based models
+
* Energy-based models
  
 
==== Dec. 2,4:  Neural implementations ====
 
==== Dec. 2,4:  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:  Guest lectures ====
 
==== Dec. 9,11:  Guest lectures ====
  
# TBD
+
* TBD
# TBD
+
* TBD

Revision as of 17:32, 1 September 2014

Syllabus

Aug. 28: Introduction

  • Theory and modeling in neuroscience
  • Goals of AI/machine learning vs. theoretical neuroscience
  • Turing vs. neural computation

Sept. 2,4: Neuron models

  • Membrane equation, compartmental model of a neuron
  • Linear systems: vectors, matrices, linear neuron models
  • Perceptron model and linear separability

Sept. 9,11: Guest lectures

  • TBD
  • Paul Rhodes, Evolved Machines: Multi-compartment models; dendritic integration

Sept. 16,18: Supervised learning

  • Perceptron learning rule
  • Adaptation in linear neurons, Widrow-Hoff rule
  • Objective functions and gradient descent
  • Multilayer networks and backpropagation

Sept. 23,25: Unsupervised learning

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

Sept. 30: Guest lecture

  • TBD

Oct. 2: Sparse, distributed coding

  • Autoencoders
  • Natural image statistics
  • Projection pursuit

Oct. 7: Plasticity and cortical maps

  • Cortical maps
  • Self-organizing maps, Kohonen nets
  • Models of experience dependent learning and cortical reorganization

Oct. 9: Guest lecture

  • TBD

Oct. 14: Manifold learning

  • Local linear embedding, Isomap

Oct. 16: Guest lecture

  • Tom Dean, Google: Connectomics

Oct. 21,23,28,30: Recurrent networks

  • Hopfield networks
  • Models of associative memory, pattern completion
  • Line attractors and `bump circuits’
  • Dynamical models

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

  • Probability theory and Bayes’ rule
  • Learning and inference in generative models
  • The mixture of Gaussians model
  • Boltzmann machines
  • Sparse coding and ‘ICA’
  • Kalman filter model
  • Energy-based models

Dec. 2,4: Neural implementations

  • Integrate-and-fire model
  • Neural encoding and decoding
  • Limits of precision in neurons
  • Neural synchrony and phase-based coding

Dec. 9,11: Guest lectures

  • TBD
  • TBD
Personal tools