Dither NN: Hardware/Algorithm Co-Design for Accurate Quantized Neural Networks
Authors:
Open Access
- 1 December 2019
- journal article
- research article
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Information and Systems
- Vol. E102.D (12) , 2341-2353
Abstract
Deep neural network (NN) has been widely accepted for enabling various AI applications, however, the limitation of computational and memory resources is a major problem on mobile devices. Quantized NN with a reduced bit precision is an effective solution, which relaxes the resource requirements, but the accuracy degradation due to its numerical approximation is another problem. We propose a novel quantized NN model employing the “dithering” technique to improve the accuracy with the minimal additional hardware requirement at the view point of the hardware-algorithm co-designing. Dithering distributes the quantization error occurring at each pixel (neuron) spatially so that the total information loss of the plane would be minimized. The experiment we conducted using the software-based accuracy evaluation and FPGA-based hardware resource estimation proved the effectiveness and efficiency of the concept of an NN model with dithering.Keywords
This publication has 9 references indexed in Scilit:
- Dither NN: An Accurate Neural Network with Dithering for Low Bit-Precision Hardware2018
- ReBNet: Residual Binarized Neural Network2018
- UNPU: A 50.6TOPS/W unified deep neural network accelerator with 1b-to-16b fully-variable weight bit-precision2018
- QUEST: A 7.49TOPS multi-purpose log-quantized DNN inference engine stacked on 96MB 3D SRAM using inductive-coupling technology in 40nm CMOS2018
- BRein Memory: A Single-Chip Binary/Ternary Reconfigurable in-Memory Deep Neural Network Accelerator Achieving 1.4 TOPS at 0.6 WIEEE Journal of Solid-State Circuits, 2017
- 14.2 DNPU: An 8.1TOPS/W reconfigurable CNN-RNN processor for general-purpose deep neural networks2017
- A 0.3–2.6 TOPS/W precision-scalable processor for real-time large-scale ConvNets2016
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016
- Energy-efficient ConvNets through approximate computing2016