5 papers
Scalable Perturbation Learning for Online Self-Supervised Learning in Echo State Networks
Taiki Yamada, Kantaro Fujiwara
Intelligent systems should not only solve tasks but also adapt under real-world constraints. Autonomous adaptation via self-supervised learning, sequential adaptation via online le…
Forman--Ricci Curvature on Contact-Sequence Temporal Networks via Spatiotemporal Prism Complexes
Taiki Yamada
Temporal networks -- sequences of time-stamped contacts among nodes -- constitute the finest-grained representation of dynamic interaction data; however, geometric and topological…
Frame Theoretical Derivation of Three Factor Learning Rule for Oja's Subspace Rule
Taiki Yamada
We show that the error-gated Hebbian rule for PCA (EGHR-PCA), a three-factor learning rule equivalent to Oja's subspace rule under Gaussian inputs, can be systematically derived fr…
Vertex evaluation of multiplex graphs using Forman Curvature
Taiki Yamada
The identification of vertices that play a central role in network analysis is a fundamental challenge. Although traditional centrality measures have been extensively employed for…
Unsupervised Learning in Echo State Networks for Input Reconstruction
Taiki Yamada, Yuichi Katori, Kantaro Fujiwara
Echo state networks (ESNs) are a class of recurrent neural networks in which only the readout layer is trainable, while the recurrent and input layers are fixed. This architectural…