.png){kind=icon}
返回
Dynamic learning rates for continual unsupervised learning
.png){kind=icon}
OA
AI
DOI：10.3233/ICA-230701.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The dilemma between stability and plasticity is crucial in machine learning, especially when non-stationary input distributions are considered. This issue can be addressed by continual learning in order to alleviate catastrophic forgetting. This strategy has been previously proposed for supervised and reinforcement learning models. However, little attention has been devoted to unsupervised learning. This work presents a dynamic learning rate framework for unsupervised neural networks that can handle non-stationary distributions. In order for the model to adapt to the input as it changes its characteristics, a varying learning rate that does not merely depend on the training step but on the reconstruction error has been proposed. In the experiments, different configurations for classical competitive neural networks, self-organizing maps and growing neural gas with either per-neuron or per-network dynamic learning rate have been tested. Experimental results on document clustering tasks demonstrate the suitability of the proposal for real-world problems.
Keyword:
Continual learning
unsupervised learning
competitive neural network
self-organizing map
growing neural gas
document clustering
期刊
I
IF:
5.3
论文数:
491
被引数:
735
机构
引用论文
Identification of homogeneous regions for regionalization of watersheds by two-level self-organizing feature maps.png)
JOURNAL OF HYDROLOGY
JOURNAL OF HYDROLOGYIF6.3
PREAI
分享收藏Deep learning techniques for recommender systems based on collaborative filteringEXPERT SYSTEMS
EXPERT SYSTEMSIF2.3
PREAI
分享收藏Practical Approach to Measuring and Reporting Friction and Macrotexture at Variable Test Speeds
PREAI
分享收藏
查看更多内容