论文标题
主题培养和奖励学习改进的尖峰神经网络，以进行有效的多感觉集成
Motif-topology and Reward-learning improved Spiking Neural Network for Efficient Multi-sensory Integration
论文作者
论文摘要
网络体系结构和学习原理是在人工神经网络（ANN）和尖峰神经网络（SNN）中形成复杂功能的关键。 SNN被视为新一代人造网络，通过合并比ANN更多的生物学特征，包括动态尖峰神经元，功能指定的体系结构和有效的学习范式。在本文中，我们提出了一个基序论和奖励学习改进的SNN（MR-SNN），以有效地多感官整合。 MR-SNN包含13种类型的3节点基序拓扑结构，这些拓扑首先是从独立的单感学习范式中提取的，然后集成以进行多感官分类。实验结果表明，与其他常规SNN相比，提出的MR-SNN的准确性和更强的鲁棒性在不使用基序的情况下更高。此外，提出的奖励学习范式在生物学上是合理的，可以更好地解释由不一致的视觉和听觉感觉信号引起的认知麦格克效应。
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.
