Efficient acceleration of deep learning inference on resource-constrained edge devices: A review

MMH Shuvo, SK Islam, J Cheng… - Proceedings of the …, 2022‏ - ieeexplore.ieee.org
Successful integration of deep neural networks (DNNs) or deep learning (DL) has resulted
in breakthroughs in many areas. However, deploying these highly accurate models for data …

Model compression and hardware acceleration for neural networks: A comprehensive survey

L Deng, G Li, S Han, L Shi, Y ** for ReRAM-based accelerator
S Yang, W Chen, X Zhang, S He, Y Yin… - Proceedings of the 35th …, 2021‏ - dl.acm.org
Emergent ReRAM-based accelerators support in-memory computation to accelerate deep
neural network (DNN) inference. Weight matrix pruning of DNNs is a widely used technique …