Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters

Abstract

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%.

References in corpus (7)

• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Post-training 4-bit quantization of convolution networks for rapid-deployment
• Reduced-Precision Strategies for Bounded Memory in Deep Neural Nets
• Fixed-Point Convolutional Neural Network for Real-Time Video Processing in FPGA
• Efficient non-uniform quantizer for quantized neural network targeting reconfigurable hardware