• Femy N S
• Dr. Sasi Gopalan

Self-Organizing Maps is an unsupervised artificial neural network that is trained to produce a low-dimensional representation of high-dimensional data. In this work, a novel approach is made by introducing lattice vectors to the input space of self-organizing maps. The algebraic and geometric properties of lattice vectors in the linear initialization method of weight initialization in self-organizing maps are studied. It is also found that each data vector in the input space of self-organizing maps will lie in the fundamental region associated with the basis vectors of the lattice. The experimental analysis is done by taking dataset from UCI machine learning repository and using MATLAB R2021a.

Determinant, Fundamental parallelepiped, Lattice vectors, Projection, Self-Organizing Maps.

"A Study of Lattice Vectors in Self-Organizing Maps", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.j413-j417, June-2022, Available :http://www.jetir.org/papers/JETIR2206956.pdf

"A Study of Lattice Vectors in Self-Organizing Maps", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppj413-j417, June-2022, Available at : http://www.jetir.org/papers/JETIR2206956.pdf