On Building Efficient and Robust Neural Network Designs
On Building Efficient and Robust Neural Network Designs
复制标题
DOI：
10.1109/ieeeconf56349.2022.10051891
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Xiaoxuan Yang;Huanrui Yang;Jingchi Zhang;Hai Helen Li;Yiran Chen
中科院分区：
文献类型：
--
作者：
Xiaoxuan Yang;Huanrui Yang;Jingchi Zhang;Hai Helen Li;Yiran Chen
神经网络模型在从图像分类到自然语言处理的各种应用中都表现出了出色的性能。然而，将模型部署到硬件上会带来效率和可靠性问题。从效率的角度来看，神经网络处理的存储、计算和通信成本相当大，因为神经网络模型具有大量的参数和操作。从鲁棒性的角度来看，硬件的扰动是不可避免的，因此神经网络的性能可能会下降。因此，本文研究了有效的学习和优化方法以及先进的硬件设计，以构建高效且鲁棒的神经网络设计。
Neural network models have demonstrated outstanding performance in a variety of applications, from image classification to natural language processing. However, deploying the models to hardware raises efficiency and reliability issues. From the efficiency perspective, the storage, computation, and communication cost of neural network processing is considerably large because the neural network models have a large number of parameters and operations. From the standpoint of robustness, the perturbation in hardware is unavoidable and thus the performance of neural networks can be degraded. As a result, this paper investigates effective learning and optimization approaches as well as advanced hardware designs in order to build efficient and robust neural network designs.