Saturation Self-Organizing Map
Continual learning poses a fundamental challenge for neural systems, which often suffer from catastrophic forgetting when exposed to sequential tasks. Self-Organizing Maps (SOMs), despite their interpretability and efficiency, are not immune to this issue. In this paper, we introduce Saturation Self-Organizing Maps (SatSOM)-an extension of SOMs designed to improve knowledge retention in continual learning scenarios. SatSOM incorporates a novel saturation mechanism that gradually reduces the learning rate and neighborhood radius of neurons as they accumulate information. This effectively freezes well-trained neurons and redirects learning to underutilized areas of the map.
Code (1)
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
Human Symmetry Uncertainty Detected by a Self-Organizing Neural Network Map
Symmetry in biological and physical systems is a product of self organization driven by evolutionary processes, or mechanical systems under constraints. Symmetry based feature extrac-tion or representation by neural netw…
QuantizationA Multi-signal Variant for the GPU-based Parallelization of Growing Self-Organizing Networks
Among the many possible approaches for the parallelization of self-organizing networks, and in particular of growing self-organizing networks, perhaps the most common one is producing an optimized, parallel implementatio…
GPUA Self-Organizing Network with Varying Density Structure for Characterizing Sensorimotor Transformations in Robotic Systems
In this work, we present the development of a neuro-inspired approach for characterizing sensorimotor relations in robotic systems. The proposed method has self-organizing and associative properties that enable it to aut…
Self-organizing traffic lights: A realistic simulation
We have previously shown in an abstract simulation (Gershenson, 2005) that self-organizing traffic lights can improve greatly traffic flow for any density. In this paper, we extend these results to a realistic setting, i…
Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis
The quality of datasets plays a crucial role in the successful training and deployment of deep learning models. Especially in the medical field, where system performance may impact the health of patients, clean datasets …
Outlier DetectionOut-of-Distribution DetectionQuantization