IEEE Trans Biomed Circuits Syst. 2015 Apr;9(2):188-96. doi: 10.1109/TBCAS.2015.2416391. Epub 2015 Apr 22.
We have added a simplified neuromorphic model of Spike Time Dependent Plasticity (STDP) to the previously described Synapto-dendritic Kernel Adapting Neuron (SKAN), a hardware efficient neuron model capable of learning spatio-temporal spike patterns. The resulting neuron model is the first to perform synaptic encoding of afferent signal-to-noise ratio in addition to the unsupervised learning of spatio-temporal spike patterns. The neuron model is particularly suitable for implementation in digital neuromorphic hardware as it does not use any complex mathematical operations and uses a novel shift-based normalization approach to achieve synaptic homeostasis. The neuron's noise compensation properties are characterized and tested on random spatio-temporal spike patterns as well as a noise corrupted subset of the zero images of the MNIST handwritten digit dataset. Results show the simultaneously learning common patterns in its input data while dynamically weighing individual afferents based on their signal to noise ratio. Despite its simplicity the interesting behaviors of the neuron model and the resulting computational power may also offer insights into biological systems.
我们在先前描述的 Synapto-dendritic Kernel Adapting Neuron (SKAN) 中添加了简化的尖峰时间依赖性可塑性 (STDP) 神经拟态模型，这是一种硬件高效的神经元模型，能够学习时空尖峰模式。由此产生的神经元模型是第一个执行传入信号与噪声比的突触编码的模型，除了时空尖峰模式的无监督学习之外。由于该神经元模型不使用任何复杂的数学运算，并采用新颖的基于移位的归一化方法来实现突触平衡，因此特别适合于数字神经拟态硬件的实现。对随机时空尖峰模式以及 MNIST 手写数字数据集的零图像的噪声污染子集进行了神经元的噪声补偿特性的特征和测试。结果表明，该神经元在输入数据中同时学习常见模式，同时根据其信号与噪声比动态权衡各个传入神经元。尽管该神经元模型的结构简单，但其有趣的行为和产生的计算能力也可能为生物系统提供新的见解。
