svm v1.0

The svm v1.0 package contains two programs:

• compute-weights trains a support vector machine based upon a given set of labeled training examples, and
• classify applies a trained support vector machine to unlabeled data to produce predicted binary classifications.

The software requires RDB, a fast, portable relational database management system that runs under Unix.

svm v1.0 is written in ANSI C. Pre-compiled versions (including source code) are available for the following platforms:

• Sun Solaris
• Sun OS
• DEC Alpha

Here are some installation instructions.

And here is the obligatory copyright notice.

The svm v1.0 software was written by William Noble Grundy in the Department of Computer Science at the University of California, Santa Cruz.