The Self-Splitting Neural Network
Scott Gordon, California State University, Sacramento
04/06/2006
A Neural Network is a popular artificial intelligence technique in which an array of simulated neurons are interconnected to form a very simplified model of a tiny brain. Knowledge is stored in the interconnections, and is typically acquired through training. In practice, this is often limited to relatively small problems. The self-splitting neural network attempts to tackle larger problems by dividing the input domain into small chunks, and assigning a separate neural network to each chunk. Using a variety of splitting methods, large problems not typically solvable with standard neural networks have been learned quickly and with excellent generalization.
Sync And Timing Issues Of Carrying Tdm Traffic Over Packet Networks
Kishan Shenoi, Symmetricom, San Jose, California
04/13/2006
Packet networks are very efficient in delivering information ("bits") between two end points. Delivery of TDM signals requires, in addition to bits, the replication of timing ("bit-time"). The talk introduces the notion of transporting bit-time and explains the four primary methods being considered in the various Standards Bodies. The advantages and disadvantages of these methods are explained.
Prototyping In Game Development
Jason Shankel, Maxis/Electronic Arts, Walnut Creek, California
04/27/2006
Prototyping is a powerful method for isolating and testing particular aspects of complex software designs. In this talk, I will discuss the use of prototyping in the development of computer games.
Application Of Genetic Programming To Fraud Detection And Security
Bill Wilson, Security Consulting, Cupertino, California
05/04/2006
Genetic Programming is a machine learning method that has been successfully applied to problems as diverse as designing radio antennas, jet engines, and analysis of the human genome. It can be used to find patterns that characterize specific types of data and transactions. This talk will give a brief introduction to genetic programming and explore its potential applications to problems in network security and financial fraud. In particular the talk will consider what specific types of problems genetic programming will most likely be able to effectively address. It will also present remaining challenges in the practical application of genetic programming to these problems.
Spring 2006 Short Presentations Of Student Research
STUDENT PRESENTATIONS
05/11/2006
Short presentations of research carried out by Sonoma State Computer Science Students