TY - GEN
T1 - Understanding SyncMap
T2 - 5th Artificial Intelligence and Cloud Computing Conference, AICCC 2022
AU - Foong, Tham Yik
AU - Vargas, Danilo Vasconcellos
N1 - Funding Information:
This work was supported by JST, ACT-I Grant Number JP-50243 and JSPS KAKENHI Grant Number JP20241216. T.Y.F. is supported by JST SPRING, Grant Number JPMJSP2136.
Publisher Copyright:
© 2022 ACM.
PY - 2022/12/17
Y1 - 2022/12/17
N2 - SycnMap has been recently proposed as an unsupervised approach to perform chunking. This model, which falls under the paradigm of self-organizing dynamical equations, can achieve learning merely using the principle of self-organization without any objective function. However, it is still poorly understood due to its novelty. Here, we provide a comprehensive analysis of the underlying dynamical equation that governed the learning of SyncMap. We first introduce several components of the dynamical equation: (1) Learning rate, (2) Dynamic noise, and (3) Coefficient of attraction force; As well as model-specific variables: (4) Input signal noise and (5) Dimension of weight space. With that, we examine their effect on the performance of SyncMap. Our study shows that the dynamic noise and dimension of weight space play an important role in the dynamical equation; By solely tuning them, the enhanced model can outperform the baseline methods as well as the original SyncMap in 6 out of 7 environments.
AB - SycnMap has been recently proposed as an unsupervised approach to perform chunking. This model, which falls under the paradigm of self-organizing dynamical equations, can achieve learning merely using the principle of self-organization without any objective function. However, it is still poorly understood due to its novelty. Here, we provide a comprehensive analysis of the underlying dynamical equation that governed the learning of SyncMap. We first introduce several components of the dynamical equation: (1) Learning rate, (2) Dynamic noise, and (3) Coefficient of attraction force; As well as model-specific variables: (4) Input signal noise and (5) Dimension of weight space. With that, we examine their effect on the performance of SyncMap. Our study shows that the dynamic noise and dimension of weight space play an important role in the dynamical equation; By solely tuning them, the enhanced model can outperform the baseline methods as well as the original SyncMap in 6 out of 7 environments.
UR - http://www.scopus.com/inward/record.url?scp=85158121960&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85158121960&partnerID=8YFLogxK
U2 - 10.1145/3582099.3582136
DO - 10.1145/3582099.3582136
M3 - Conference contribution
AN - SCOPUS:85158121960
T3 - ACM International Conference Proceeding Series
SP - 246
EP - 254
BT - Proceedings of the 2022 5th Artificial Intelligence and Cloud Computing Conference, AICCC 2022
PB - Association for Computing Machinery
Y2 - 17 December 2022 through 19 December 2022
ER -