# Difference between revisions of "VS265: Syllabus"

### From RedwoodCenter

(→Sept. 30: Guest lecture) |
|||

Line 14: | Line 14: | ||

==== Sept. 9,11: Guest lectures ==== | ==== Sept. 9,11: Guest lectures ==== | ||

− | * | + | * 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 | + | * Fritz Sommer: Associative memories and attractor neural networks |

− | ==== Oct. | + | ==== 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. | + | ==== 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. | + | ==== Oct. 28: Manifold learning ==== |

− | + | ||

− | + | ||

− | + | ||

− | + | ||

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

− | ==== Oct. | + | ==== Oct. 30, Nov. 4,6: Recurrent networks ==== |

− | + | ||

− | + | ||

− | + | * Hopfield networks, memories as 'basis of attraction' | |

− | * Hopfield networks | + | |

− | + | ||

* Line attractors and `bump circuits’ | * Line attractors and `bump circuits’ | ||

* Dynamical models | * Dynamical models | ||

− | ==== Nov. | + | ==== 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: | + | ==== Dec. 9,11: Special topics ==== |

* TBD | * TBD | ||

* TBD | * TBD |

## Revision as of 19:07, 14 October 2014

## Contents

- 1 Syllabus
- 1.1 Aug. 28: Introduction
- 1.2 Sept. 2,4: Neuron models
- 1.3 Sept. 9,11: Guest lectures
- 1.4 Sept. 16,18: Supervised learning
- 1.5 Sept. 23,25: Unsupervised learning
- 1.6 Sept. 30, Oct. 2: Guest lecture
- 1.7 Oct. 7,9: Guest lectures
- 1.8 Oct. 14: Unsupervised learning (continued)
- 1.9 Oct. 16: Guest lecture
- 1.10 Oct. 21: Sparse, distributed coding
- 1.11 Oct. 23: Plasticity and cortical maps
- 1.12 Oct. 28: Manifold learning
- 1.13 Oct. 30, Nov. 4,6: Recurrent networks
- 1.14 Nov. 13,18,20,25: Probabilistic models and inference
- 1.15 Dec. 2,4: Neural implementations
- 1.16 Dec. 9,11: Special topics

## 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

- Matlab/Python tutorial
- 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, Oct. 2: Guest lecture

- Fritz Sommer: Associative memories and attractor neural networks

#### 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
- Natural image statistics
- Projection pursuit

#### Oct. 23: Plasticity and cortical maps

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

#### Oct. 28: Manifold learning

- Local linear embedding, Isomap

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

- Hopfield networks, memories as 'basis of attraction'
- Line attractors and `bump circuits’
- Dynamical models

#### Nov. 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: Special topics

- TBD
- TBD