QoS Scheduling with Opportunistic Spectrum Access for Multimedia

2012 ◽  
pp. 162-178
Author(s):  
Pavol Polacek ◽  
Chih-Wei Huang
Keyword(s):  
User Experience ◽  
Research Effort ◽  
Research Area ◽  
Opportunistic Spectrum Access ◽  
System Capacity ◽  
Research Trend ◽  
Spectrum Access ◽  
Computing Platform ◽  
Resource Limited ◽  
Application Data

Thanks to the advances of multimedia application, mobile computing platform, and wireless communication technology, the research area has attracted serious attention in order to seamlessly provide interactive and ubiquitous user experience. To make it happen, the pursuit of higher system capacity in resource limited wireless networks is never-ending. Cognitive radio (CR) represents an exciting new communication paradigm with advantages on spectrum management so as to heighten channel utilization and capacity. The bandwidth demanding multimedia applications are excellent candidates to fully exploit the potential of CR. However, the research effort has been focused mainly on spectrum access while the application specific performance has been much less touched. The research considering both spectrum access and application data scheduling is emerging for maximal user experience. In this chapter, the authors first discuss advances in opportunistic spectrum access (OSA) strategies as well as multimedia QoS scheduling schemes, and then introduce the research trend on joint access and scheduling frameworks.

scholarly journals Harmonious Coexistence of Structured Weight Pruning and Ternarization for Deep Neural Networks

2020 ◽  
Vol 34 (04) ◽  
pp. 6623-6630
Author(s):  
Li Yang ◽  
Zhezhi He ◽  
Deliang Fan
Keyword(s):  
Embedded System ◽  
Processing Elements ◽  
Computing Platform ◽  
Model Compression ◽  
Computing Unit ◽  
Resource Limited ◽  
Adopted Model ◽  
Weight Penalty ◽  
Model Size ◽  
Weight Pruning

Deep convolutional neural network (DNN) has demonstrated phenomenal success and been widely used in many computer vision tasks. However, its enormous model size and high computing complexity prohibits its wide deployment into resource limited embedded system, such as FPGA and mGPU. As the two most widely adopted model compression techniques, weight pruning and quantization compress DNN model through introducing weight sparsity (i.e., forcing partial weights as zeros) and quantizing weights into limited bit-width values, respectively. Although there are works attempting to combine the weight pruning and quantization, we still observe disharmony between weight pruning and quantization, especially when more aggressive compression schemes (e.g., Structured pruning and low bit-width quantization) are used. In this work, taking FPGA as the test computing platform and Processing Elements (PE) as the basic parallel computing unit, we first propose a PE-wise structured pruning scheme, which introduces weight sparsification with considering of the architecture of PE. In addition, we integrate it with an optimized weight ternarization approach which quantizes weights into ternary values ({-1,0,+1}), thus converting the dominant convolution operations in DNN from multiplication-and-accumulation (MAC) to addition-only, as well as compressing the original model (from 32-bit floating point to 2-bit ternary representation) by at least 16 times. Then, we investigate and solve the coexistence issue between PE-wise Structured pruning and ternarization, through proposing a Weight Penalty Clipping (WPC) technique with self-adapting threshold. Our experiment shows that the fusion of our proposed techniques can achieve the best state-of-the-art ∼21× PE-wise structured compression rate with merely 1.74%/0.94% (top-1/top-5) accuracy degradation of ResNet-18 on ImageNet dataset.

Sign in / Sign up

Export Citation Format

Share Document