We present an end-to-end trainable modular event-driven neural architecture that uses local synaptic and threshold adaptation rules to perform transformations between arbitrary spatio-temporal spike patterns. The architecture represents a highly abstracted model of existing Spiking Neural Network (SNN) architectures. The proposed Optimized Deep Event-driven Spiking neural network Architecture (ODESA) can simultaneously learn hierarchical spatio-temporal features at multiple arbitrary time scales. ODESA performs online learning without the use of error back-propagation or the calculation of gradients. Through the use of simple local adaptive selection thresholds at each node, the network rapidly learns to appropriately allocate its neuronal resources at each layer for any given problem without using a real-valued error measure. These adaptive selection thresholds are the central feature of ODESA, ensuring network stability and remarkable robustness to noise as well as to the selection of initial system parameters. Network activations are inherently sparse due to a hard Winner-Take-All (WTA) constraint at each layer. We evaluate the architecture on existing spatio-temporal datasets, including the spike-encoded IRIS and TIDIGITS datasets, as well as a novel set of tasks based on International Morse Code that we created. These tests demonstrate the hierarchical spatio-temporal learning capabilities of ODESA. Through these tests, we demonstrate ODESA can optimally solve practical and highly challenging hierarchical spatio-temporal learning tasks with the minimum possible number of computing nodes.
翻译:我们展示了一个端到端可训练的模块式事件驱动神经结构,该结构使用本地合成和阈值调整规则,在任意的时空螺旋钉模式之间进行转换。该结构代表了现有Spiking神经网络(SNN)结构的高度抽象模型。拟议的优化事件驱动神经网络架构(OSDEA)可以同时学习多个任意时间尺度的等级空间-时空特征。 OSDEA进行在线学习,不使用实际的反演错误或梯度计算。通过在每一个节点使用简单的本地适应性选择阈值,网络迅速学会如何在每一个层为任何特定问题适当分配神经资源,而不使用真实的错误测量。这些适应性选择阈值是ODESA的核心特征,确保网络的稳定性和对噪音以及初始系统参数的选取。 网络启动本质上是稀少的,因为每个层都有硬性Winner-Take-A(WTA) 的精确度-直观性调整或计算梯度限制。我们通过每个节点使用简单本地的系统选择标准选择,通过每个节点选择,对每个节点进行简单的本地的系统选择,我们在每一层-时间级选择数据测试时段的系统测试中,我们评估了现有的空间-时间-时间级选择数据测试,我们对每个层的系统测试,我们评估了每个层-空间-空间-空间-时间级数据测试,这些测试的系统测试显示的系统测试显示的系统测试,这些测试显示的系统-智能数据能力,这些测试,这些测试的系统测试的系统测试显示的系统测试,这些测试显示的系统测试,这些测试显示的系统测试显示这些测试。