Implementation of Kohonen's Self-Organizing Maps on MANTRA I

Reprinted from This paper presents a computer dedicated to neu-ral algorithms. The computational core of the system is a systolic array of dedicated Processing Elements (PEs). This accelerator provides the primitives to implement several widely used neural models, including Kohonen's Self-Organizing Maps (SOMs). This paper concentrates on the problems related to the mapping of the SOM algorithm on the machine. Some modii-cations to the algorithm, required to parallelize it ee-ciently, are also proposed. Some aspects of the complexity of programming a systolic system are discussed and the chosen software approach is presented.