Quant-pim: An energy-efficient processing-in-memory accelerator for layerwise quantized neural networks

YS Lee, EY Chung, YH Gong… - IEEE Embedded …, 2021 - ieeexplore.ieee.org
Layerwise quantized neural networks (QNNs), which adopt different precisions for weights
or activations in a layerwise manner, have emerged as a promising approach for embedded …

Quant-PIM: An Energy-Efficient Processing-in-Memory Accelerator for Layerwise Quantized Neural Networks

YS Lee, EY Chung, YH Gong… - IEEE EMBEDDED …, 2021 - scholarworks.bwise.kr
Layerwise quantized neural networks (QNNs), which adopt different precisions for weights
or activations in a layerwise manner, have emerged as a promising approach for embedded …

[PDF][PDF] Quant-PIM: An Energy-efficient Processing-in-memory Accelerator for Layer-wise Quantized Neural Networks

YS Lee, EY Chung, YH Gong, SW Chung - dtl.yonsei.ac.kr
Layer-wise quantized neural networks (QNNs), which adopt different precisions for weights
or activations in a layer-wise manner, have emerged as a promising approach for …

Quant-PIM: An Energy-Efficient Processing-in-Memory Accelerator for Layerwise Quantized Neural Networks

YS Lee, EY Chung, YH Gong… - IEEE Embedded …, 2021 - yonsei.elsevierpure.com
Layerwise quantized neural networks (QNNs), which adopt different precisions for weights
or activations in a layerwise manner, have emerged as a promising approach for embedded …

Quant-PIM: An Energy-Efficient Processing-in-Memory Accelerator for Layerwise Quantized Neural Networks

YS Lee, EY Chung, YH Gong, SW Chung - IEEE Embedded Systems …, 2021 - dl.acm.org
Layerwise quantized neural networks (QNNs), which adopt different precisions for weights
or activations in a layerwise manner, have emerged as a promising approach for embedded …

Quant-PIM: An Energy-efficient Processing-in-memory Accelerator for Layer-wise Quantized Neural Networks

YS Lee, EY Chung, YH Gong… - IEEE Embedded Systems …, 2021 - pure.korea.ac.kr
Layer-wise quantized neural networks (QNNs), which adopt different precisions for weights
or activations in a layer-wise manner, have emerged as a promising approach for …