Binarized neural networks, or BNNs, show great promise in edge-side applications with resource limited hardware, but raise the concerns of reduced accuracy. Motivated by the complex neural networks, in this paper we introduce complex representation into the BNNs and propose Binary complex neural network -- a novel network design that processes binary complex inputs and weights through complex convolution, but still can harvest the extraordinary computation efficiency of BNNs. To ensure fast convergence rate, we propose novel BCNN based batch normalization function and weight initialization function. Experimental results on Cifar10 and ImageNet using state-of-the-art network models (e.g., ResNet, ResNetE and NIN) show that BCNN can achieve better accuracy compared to the original BNN models. BCNN improves BNN by strengthening its learning capability through complex representation and extending its applicability to complex-valued input data. The source code of BCNN will be released on GitHub.

中文翻译：

---

BCNN：二进制复杂神经网络

二值化神经网络或BNN在具有有限资源的硬件的边端应用中显示出巨大的希望，但引发了降低精度的担忧。在复杂神经网络的推动下，本文将复杂表示引入BNN，并提出二进制复杂神经网络-一种通过复杂卷积处理二进制复杂输入和权重的新颖网络设计，但仍可以收获BNN的非凡计算效率。为了确保快速收敛速度，我们提出了基于BCNN的批处理归一化函数和权重初始化函数。使用最新的网络模型（例如ResNet，ResNetE和NIN）在Cifar10和ImageNet上进行的实验结果表明，与原始BNN模型相比，BCNN可以实现更好的准确性。BCNN通过增强通过复杂表示的学习能力并将其适用性扩展到复杂值输入数据来改进BNN。BCNN的源代码将在GitHub上发布。