Spiking Neural Networks (SNNs) are a promising paradigm for efficient event-driven processing of spatio-temporally sparse data streams. SNNs have inspired the design and can take advantage of the emerging class of neuromorphic processors like Intel Loihi. These novel hardware architectures expose a variety of constraints that affect firmware, compiler and algorithm development alike. To enable rapid and flexible development of SNN algorithms on Loihi, we developed NxTF: a programming interface derived from Keras and compiler optimized for mapping deep convolutional SNNs to the multi-core Intel Loihi architecture. We evaluate NxTF on DNNs trained directly on spikes as well as models converted from traditional DNNs, processing both sparse event-based and dense frame-based data sets. Further, we assess the effectiveness of the compiler to distribute models across a large number of cores and to compress models by exploiting Loihi's weight sharing features. Finally, we evaluate model accuracy, energy and time to solution compared to other architectures. The compiler achieves near optimal resource utilization of 80% across 16 Loihi chips for a 28-layer, 4M parameter MobileNet model with input size 128x128. In addition, we report the lowest error rate of 8.52% for the CIFAR-10 dataset on neuromorphic hardware, using an off-the-shelf MobileNet.

中文翻译：

---

NxTF：英特尔Loihi上用于深度掺入神经网络的API和编译器

尖刺神经网络（SNN）是有效的事件驱动的时空稀疏数据流处理的有希望的范例。SNN激发了设计灵感，并可以利用诸如Intel Loihi之类的新兴神经形态处理器。这些新颖的硬件体系结构暴露了各种影响固件，编译器和算法开发的约束。为了在Loihi上快速灵活地开发SNN算法，我们开发了NxTF：一种从Keras派生的编程接口，并针对将深度卷积SNN映射到多核Intel Loihi架构进行了优化。我们评估直接在峰值上训练的DNN上的NxTF以及从传统DNN转换而来的模型，同时处理基于事件和稀疏数据的稀疏数据集。进一步，我们评估了编译器通过利用Loihi的权重共享功能在多个内核之间分配模型并压缩模型的有效性。最后，与其他架构相比，我们评估模型的准确性，精力和解决问题的时间。对于输入大小为128x128的28层4M参数MobileNet模型，该编译器可在16个Loihi芯片上实现接近80％的最佳资源利用率。此外，我们使用现成的MobileNet报告了神经形态硬件上CIFAR-10数据集的最低错误率8.52％。对于输入大小为128x128的28层4M参数MobileNet模型，该编译器可在16个Loihi芯片上实现接近80％的最佳资源利用率。此外，我们使用现成的MobileNet报告了神经形态硬件上CIFAR-10数据集的最低错误率8.52％。对于输入大小为128x128的28层4M参数MobileNet模型，该编译器可在16个Loihi芯片上实现接近80％的最佳资源利用率。此外，我们使用现成的MobileNet报告了神经形态硬件上CIFAR-10数据集的最低错误率8.52％。