University of California, Irvine (UCI)
School of Information and Computer Sciences (ICS)
Center for Machine Learning and Intelligent Systems (CML)
  Institute for Genomics and Bioinformatics (IGB)

Neural Networks

ICS 276A
Pierre Baldi


Course - Prerequisites - Textbooks - Grading

Course Goals and Description

This is a graduate level course on neural networks. The course covers the following topics:

bullet Historical introduction. Connections to biological modeling, computational neuroscience, and cognitive modeling. Artificial/Natural NNs.
bullet Basic concepts of feedforward networks. Single layer perceptrons. Multi-layer perceptrons Activation functions. Higher-order NNs. Error functions. Regression. Classification.
bullet Universal approximation properties.
bullet Bayesian probabilistic framework and Bayesian statistical approach to NNs. Maximum likelihood approaches.
bullet Learning. Gradient Descent. Backpropagation.
bullet Recurrent NNs. Learning in recurrent NNs.
bullet NN differential equations.Dynamical systems.
bullet Hopfield model. Bolotzmann machines. Optimization.
bullet Unsupervised learning. K-means. Self-organizing maps.
bullet Bias-variance tradeoffs.
bullet Weight sharing. Cross validation methods. Weight decay. Ensemble methods.

NNs will be applied to a variety of data sets including time series and spatial data in diverse fields ranging from biology to finance.

The official catalog description is:

ICS 276A: Introduction to concepts of artificial neural networks (ANNs). Architectures for supervised and unsupervised networks. Mathematics of learning and performance rules.



Course - Prerequisites - Textbooks - Grading


A basic understanding of discrete and continuous mathematics, calculus, and probability theory, as well as proficiency in programming, or consent of instructor.



Course - Prerequisites - Textbooks - Grading


Neural Networks for Pattern Recognition by Christopher M. Bishop (Oxford University Press)

Bioinformatics: the Machine Learning Approach by Pierre Baldi and Soren Brunak (MIT Press)



Course - Prerequisites - Textbooks - Grading


Students will read articles from the literature. Grading will be based on participation in class discussions,  one exam, and a project with final presentation resulting in a brief (5--10 pages) conference-style written report. Additional assignments can include homeworks.


Back to Courses

© 2024 Pierre Baldi | pfbaldi [at] uci [dot] edu