| Title | Exploiting Resiliency for Kernel-Wise CNN Approximation Enabled by Adaptive Hardware Design |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | De la Parra, Cecilia, El-Yamany, Ahmed, Soliman, Taha, Kumar, Akash, Wehn, Norbert, Guntoro, Andre |
| Conference Name | 2021 IEEE International Symposium on Circuits and Systems (ISCAS) |
| Keywords | AI Accelerator, CNN inference, Computer architecture, Hardware, image classification, neural network resiliency, Proposals, pubcrawl, Quantization (signal), resilience, Resiliency, Space exploration |
| Abstract | Efficient low-power accelerators for Convolutional Neural Networks (CNNs) largely benefit from quantization and approximation, which are typically applied layer-wise for efficient hardware implementation. In this work, we present a novel strategy for efficient combination of these concepts at a deeper level, which is at each channel or kernel. We first apply layer-wise, low bit-width, linear quantization and truncation-based approximate multipliers to the CNN computation. Then, based on a state-of-the-art resiliency analysis, we are able to apply a kernel-wise approximation and quantization scheme with negligible accuracy losses, without further retraining. Our proposed strategy is implemented in a specialized framework for fast design space exploration. This optimization leads to a boost in estimated power savings of up to 34% in residual CNN architectures for image classification, compared to the base quantized architecture. |
| DOI | 10.1109/ISCAS51556.2021.9401517 |
| Citation Key | de_la_parra_exploiting_2021 |
Exploiting Resiliency for Kernel-Wise CNN Approximation Enabled by Adaptive Hardware Design