Abstract
A neural network model to solve analogical equations between strings of symbols is proposed. The method transforms the input strings into two fixed size alignment matrices. The matrices act as the input of the neural network which predicts two output matrices. Finally, a string decoder transforms the predicted matrices into the final string output. By design, the neural network is constrained by several properties of analogy. The experimental results show a fast learning rate with a high prediction accuracy that can beat a baseline algorithm.
| Original language | English |
|---|---|
| Pages (from-to) | 67-76 |
| Number of pages | 10 |
| Journal | CEUR Workshop Proceedings |
| Volume | 1815 |
| Publication status | Published - 2016 Jan 1 |
| Event | 24th International Conference on Case-Based Reasoning Workshops, ICCBR-WS 2016 - Atlanta, United States Duration: 2016 Oct 31 → 2016 Nov 2 |
Keywords
- Neural networks
- Proportional analogy
ASJC Scopus subject areas
- Computer Science(all)
Fingerprint Dive into the research topics of 'Solving analogical equations between strings of symbols using neural networks'. Together they form a unique fingerprint.
Cite this
Kaveeta, V., & Lepage, Y. (2016). Solving analogical equations between strings of symbols using neural networks. CEUR Workshop Proceedings, 1815, 67-76.