Symmetrical SyncMap for Imbalanced General Chunking Problems
This addresses the problem of learning complex structures from sequences in imbalanced and dynamic settings for researchers in unsupervised learning, though it appears incremental as it builds on the original SyncMap method.
The paper tackled imbalanced continual general chunking problems by proposing Symmetrical SyncMap, which uses symmetrical activation and memory windows to create stable dynamical equations, surpassing or tying unsupervised state-of-the-art baselines in all 12 imbalanced CGCPs and outperforming other methods in 3 out of 4 real-world scenarios.
Recently, SyncMap pioneered an approach to learn complex structures from sequences as well as adapt to any changes in underlying structures. This is achieved by using only nonlinear dynamical equations inspired by neuron group behaviors, i.e., without loss functions. Here we propose Symmetrical SyncMap that goes beyond the original work to show how to create dynamical equations and attractor-repeller points which are stable over the long run, even dealing with imbalanced continual general chunking problems (CGCPs). The main idea is to apply equal updates from negative and positive feedback loops by symmetrical activation. We then introduce the concept of memory window to allow for more positive updates. Our algorithm surpasses or ties other unsupervised state-of-the-art baselines in all 12 imbalanced CGCPs with various difficulties, including dynamically changing ones. To verify its performance in real-world scenarios, we conduct experiments on several well-studied structure learning problems. The proposed method surpasses substantially other methods in 3 out of 4 scenarios, suggesting that symmetrical activation plays a critical role in uncovering topological structures and even hierarchies encoded in temporal data.