[17p-WL1_301-1~13] Neuromorphic computing at the convergence of biology, electronics, and photonics

2:50 PM - 3:15 PM JST(5:50 AM - 6:15 AM UTC)

[17p-WL1_301-5] Reservoir Computing–Based Predictive Coding for Multisensory Integration and Noise-Adaptive Neural Processing

〇Yuichi Katori¹ (1.Future University Hakodate)

Keywords:

reservoir computing,Predictive Coding,Multisensory Integration

Predictive coding models cortical perception as an interaction between internally generated predictions and sensory inputs. In this talk, I introduce a predictive coding framework based on reservoir computing, which provides a nonlinear dynamical substrate that operates with minimal training. The proposed model consists of multiple reservoirs that process auditory and visual signals and enables multisensory integration with robustness to sensory noise. By exploiting intrinsic reservoir dynamics, the framework supports adaptive and stable neural processing under varying noise conditions, offering a biologically inspired approach to dynamic and noise-robust neural computation.