BCNN: Binary Complex Neural Network
This work improves BNNs for edge-side applications with resource-limited hardware by enhancing learning capability and extending applicability to complex-valued input data.
The paper tackles the accuracy reduction problem in binarized neural networks (BNNs) by introducing complex representation, proposing Binary Complex Neural Network (BCNN) which achieves better accuracy than original BNN models on Cifar10 and ImageNet datasets using ResNet, ResNetE and NIN architectures.
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.