Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters
This work addresses memory constraints for deploying DNNs on resource-limited devices like mobile phones, though it is incremental as it builds on existing quantization methods.
The paper tackles the problem of high memory requirements for deep neural networks (DNNs) in mobile and embedded systems by proposing a low-bit quantization method with dynamic and non-uniform techniques, resulting in a 50% reduction in memory footprint with only a 2.7% drop in performance as measured by the STOI metric in a speech enhancement application.
Effective employment of deep neural networks (DNNs) in mobile devices and embedded systems is hampered by requirements for memory and computational power. This paper presents a non-uniform quantization approach which allows for dynamic quantization of DNN parameters for different layers and within the same layer. A virtual bit shift (VBS) scheme is also proposed to improve the accuracy of the proposed scheme. Our method reduces the memory requirements, preserving the performance of the network. The performance of our method is validated in a speech enhancement application, where a fully connected DNN is used to predict the clean speech spectrum from the input noisy speech spectrum. A DNN is optimized and its memory footprint and performance are evaluated using the short-time objective intelligibility, STOI, metric. The application of the low-bit quantization allows a 50% reduction of the DNN memory footprint while the STOI performance drops only by 2.7%.