Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures
Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures
复制标题
用于提高基于忆阻器的神经形态架构性能的参数探索
DOI：
10.1109/tmscs.2017.2761231
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Pierre Boulet
中科院分区：
文献类型：
--
作者：
Mahyar Shahsavari;Pierre Boulet
大脑启发的尖峰神经网络神经形态架构提供了一个很有前途的解决方案，在一个非常低的功耗的认知计算任务。由于硬件实现的实际可行性，我们提出了一个基于忆阻器的硬件尖峰神经网络模型，我们模拟神经网络可扩展尖峰模拟器（N2S3），我们的开源神经形态架构模拟器。尽管Spiking神经网络在计算神经科学和神经形态计算领域得到了广泛的应用，但如何选择最佳参数以提高识别效率仍是一个亟待解决的问题。在我们的模拟器的帮助下，我们分析和评估不同的参数，如神经元的数量，STDP窗口，神经元阈值，输入尖峰的分布，和忆阻器模型参数对MNIST手写数字识别问题的影响。我们表明，仔细选择几个参数（神经元的数量，突触的种类，STDP窗口，神经元阈值）可以显着提高识别率在这个基准（约15个点的改善神经元的数量，几个点的其他）与4到5个点的识别率的变化，由于随机初始化的突触权重。
The brain-inspired spiking neural network neuromorphic architecture offers a promising solution for a wide set of cognitive computation tasks at a very low power consumption. Due to the practical feasibility of hardware implementation, we present a memristor-based model of hardware spiking neural networks which we simulate with Neural Network Scalable Spiking Simulator (N2S3), our open source neuromorphic architecture simulator. Although Spiking neural networks are widely used in the community of computational neuroscience and neuromorphic computation, there is still a need for research on the methods to choose the optimum parameters for better recognition efficiency. With the help of our simulator, we analyze and evaluate the impact of different parameters such as number of neurons, STDP window, neuron threshold, distribution of input spikes, and memristor model parameters on the MNIST hand-written digit recognition problem. We show that a careful choice of a few parameters (number of neurons, kind of synapse, STDP window, and neuron threshold) can significantly improve the recognition rate on this benchmark (around 15 points of improvement for the number of neurons, a few points for the others) with a variability of four to five points of recognition rate due to the random initialization of the synaptic weights.
DOI：
10.1073/pnas.0600676103
发表时间：
2006-06-06
影响因子：
11.1
作者：
Drew, Patrick J.;Abbott, L. F.
通讯作者：
Abbott, L. F.