Motif-topology and Reward-learning improved Spiking Neural Network for Efficient Multi-sensory Integration
This work addresses multi-sensory classification for applications in biologically-inspired AI, but it appears incremental as it builds on existing SNN methods with specific topological and learning enhancements.
The paper tackled efficient multi-sensory integration by proposing a Motif-topology and Reward-learning improved Spiking Neural Network (MR-SNN), which achieved higher accuracy and stronger robustness compared to conventional SNNs without Motifs, and better explained the cognitive McGurk effect.
Network architectures and learning principles are key in forming complex functions in artificial neural networks (ANNs) and spiking neural networks (SNNs). SNNs are considered the new-generation artificial networks by incorporating more biological features than ANNs, including dynamic spiking neurons, functionally specified architectures, and efficient learning paradigms. In this paper, we propose a Motif-topology and Reward-learning improved SNN (MR-SNN) for efficient multi-sensory integration. MR-SNN contains 13 types of 3-node Motif topologies which are first extracted from independent single-sensory learning paradigms and then integrated for multi-sensory classification. The experimental results showed higher accuracy and stronger robustness of the proposed MR-SNN than other conventional SNNs without using Motifs. Furthermore, the proposed reward learning paradigm was biologically plausible and can better explain the cognitive McGurk effect caused by incongruent visual and auditory sensory signals.