Vestibular reservoir computing
For researchers in physical reservoir computing, this work addresses the hardware complexity bottleneck by introducing a simpler uncoupled topology that matches the performance of traditional coupled reservoirs.
This paper proposes a physical reservoir computing scheme inspired by the biological vestibular system, using an uncoupled topology that achieves performance comparable to fully coupled networks. The authors derive a memory capacity formula for linear reservoirs and show that the uncoupled design offers a practical pathway for efficient physical implementations.
Reservoir computing (RC) is a computational framework known for its training efficiency, making it ideal for physical hardware implementations. However, realizing the complex interconnectivity of traditional reservoirs in physical systems remains a significant challenge. This paper proposes a physical RC scheme inspired by the biological vestibular system. To overcome hardware complexity, we introduce a designed uncoupled topology and demonstrate that it achieves performance comparable to fully coupled networks. We theoretically analyze the difference between these topologies by deriving a memory capacity formula for linear reservoirs, identifying specific conditions where both configurations yield equivalent memory. These analytical results are demonstrated to approximately hold for nonlinear reservoir systems. Furthermore, we systematically examine the impact of reservoir size on predictive statistics and memory capacity. Our findings suggest that uncoupled reservoir architectures offer a mathematically sound and practically feasible pathway for efficient physical reservoir computing.