# Self-Organizing Maps with Variable Input Length for Motif Discovery and Word Segmentation

## TL;DR

This paper introduces VILMAP, a self-organizing map model capable of discovering motifs of varying lengths in time series and segmenting words, demonstrating superior or comparable performance to existing methods.

## Contribution

The novel VILMAP model extends self-organizing maps to handle variable input lengths for motif discovery and word segmentation tasks.

## Key findings

- VILMAP effectively finds motifs of different lengths in time series.
- VILMAP avoids catastrophic forgetting with increasing input sizes.
- VILMAP achieves comparable or better results than existing methods in word segmentation.

## Abstract

Time Series Motif Discovery (TSMD) is defined as searching for patterns that are previously unknown and appear with a given frequency in time series. Another problem strongly related with TSMD is Word Segmentation. This problem has received much attention from the community that studies early language acquisition in babies and toddlers. The development of biologically plausible models for word segmentation could greatly advance this field. Therefore, in this article, we propose the Variable Input Length Map (VILMAP) for Motif Discovery and Word Segmentation. The model is based on the Self-Organizing Maps and can identify Motifs with different lengths in time series. In our experiments, we show that VILMAP presents good results in finding Motifs in a standard Motif discovery dataset and can avoid catastrophic forgetting when trained with datasets with increasing values of input size. We also show that VILMAP achieves results similar or superior to other methods in the literature developed for the task of word segmentation.