Spiking Neural Network (SNN) is considered more biologically realistic and power-efficient as it imitates the fundamental mechanism of the human brain. Recently, backpropagation (BP) based SNN learning algorithms that utilize deep learning frameworks have achieved good performance. However, bio-interpretability is partially neglected in those BP-based algorithms. Toward bio-plausible BP-based SNNs, we consider three properties in modeling spike activities: Multiplicity, Adaptability, and Plasticity (MAP). In terms of multiplicity, we propose a Multiple-Spike Pattern (MSP) with multiple spike transmission to strengthen model robustness in discrete time-iteration. To realize adaptability, we adopt Spike Frequency Adaption (SFA) under MSP to decrease spike activities for improved efficiency. For plasticity, we propose a trainable convolutional synapse that models spike response current to enhance the diversity of spiking neurons for temporal feature extraction. The proposed SNN model achieves competitive performances on neuromorphic datasets: N-MNIST and SHD. Furthermore, experimental results demonstrate that the proposed three aspects are significant to iterative robustness, spike efficiency, and temporal feature extraction capability of spike activities. In summary, this work proposes a feasible scheme for bio-inspired spike activities with MAP, offering a new neuromorphic perspective to embed biological characteristics into spiking neural networks.
翻译:由于模仿人类大脑的基本机制,Spik Spik NealNetwork(SNN)被认为在生物上更现实,更具有动力效率。最近,利用深层次学习框架的基于后推进(BP)的SNN学习算法取得了良好的业绩。然而,在基于BP的算法中,生物解释被部分忽视。在基于BP的算法中,我们考虑在模拟峰值活动中的三个属性:多重性、可适应性和可塑性(MAP)。在多重性方面,我们提出了具有多重峰值传输的多功能模式(MSP),以加强不连续神经特征的模型的稳健性。为了实现适应性,我们在MSP采用基于SN的基于SNN的SNN学习算法(SFA) 的SFA值调整法(SFA) 来减少提高效率的峰值活动。关于造型模型的可训练性演动性脉动性神经元体反应,以强化时间特征提取。在神经变形数据集(N-MNIST和SHD)上取得了竞争性的性表现。此外,实验性结果显示,在模型上层结构模型中展示了一个新的结构结构结构上层活动。