We are interested in engineering smart machines that enable backtracking of emergent behaviors. Our SSNNS simulator consists of hand-picked tools to explore spiking neural network...
Heike Sichtig, J. David Schaffer, Craig B. Laramee
As a new pattern classification method, nearest feature line (NFL) provides an effective way to tackle the sort of pattern recognition problems where only limited data are availab...
We explore the following problem: given a collection of creases on a piece of paper, each assigned a folding direction of mountain or valley, is there a flat folding by a sequenc...
Esther M. Arkin, Michael A. Bender, Erik D. Demain...
For the tasks of classification, two types of patterns can generate problems: ambiguous patterns and outliers. Furthermore, it is possible to separate classification algorithms in...
Jonathan Milgram, Mohamed Cheriet, Robert Sabourin
We propose a method for interpolation between eigenspaces. Techniques that represent observed patterns as multivariate normal distribution have actively been developed to make it r...