CS 778 – Topics in
Neural Networks and Machine Learning

Readings

__Hopfield Networks__

Required: Hopfield
and Tank

Optional: Hopfield
Chapter

Slides: Hopfield

__Boltzmann Machines__

Required: Original
Boltzmann

Optional:

Slides: Boltzmann

__Speech Recognition__

Required:

__Active Learning__

Required: Improving Generalization
with Active Learning

Optional: Survey Paper

__Bayesian Model Averaging__

Required: Bayesian
Model Averaging and Overfitting

Optional: Statistics
Field Survey Paper

__Spiking Neural Networks__

Required: Spiking
Overview - Chapter 2 required, other chapters optional

Required: SpikeProp
Paper

__Ripper____ ____Rule Learning Algorithm__

Required: Ripper

Optional: Mitchell, T., Machine Learning, Ch.
10.1-10.3

__Feature Selection: Filters and Wrappers, etc.__

Required: Wrappers and
Filters

Optional: Overview
of Feature Selection

__Kalman Filters and Extensions__

Required: Kalman Filter
Overview - pp. 15-37 required, other optional

Optional: __http://en.wikipedia.org/wiki/Kalman_filter__

Optional: Training Neural
Networks with the Extended Kalman Filter

__Non-Linear Dimensionality Reduction__

Required: Kernel PCA
Algorithm

Optional: Longer
Version Kernel PCA Algorithm Paper

Optional: Overview
Paper of Manifold Learning (Non-Linear Dimensionality Reduction)

__Bias/Variance Decomposition__

Required: Bias Plus
Variance Decomposition for Zero-One Loss Functions

__Unsupervised Learning/Clustering__

Required: Clustering
Overview

Required: Incremental
Concept Formation/Conceptual Clustering/Cobweb

Slides for study: