计算机科学
激活函数
软件部署
非线性系统
人工神经网络
二次方程
功能(生物学)
数学优化
工作(物理)
人工智能
数学
工程类
量子力学
进化生物学
机械工程
生物
操作系统
物理
几何学
作者
Zirui Xu,Jinjun Xiong,Fuxun Yu,Xiang Chen
标识
DOI:10.48550/arxiv.2011.10813
摘要
Previous works proved that the combination of the linear neuron network with nonlinear activation functions (e.g. ReLu) can achieve nonlinear function approximation. However, simply widening or deepening the network structure will introduce some training problems. In this work, we are aiming to build a comprehensive second-order CNN implementation framework that includes neuron/network design and system deployment optimization.
科研通智能强力驱动
Strongly Powered by AbleSci AI