ConformalLayers: A non-linear sequential neural network with associative layers
2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)(2021)
摘要
Convolutional Neural Networks (CNNs) have been widely applied. But as the CNNs grow, the number of arithmetic operations and memory footprint also increase. Furthermore, typical non-linear activation functions do not allow associativity of the operations encoded by consecutive layers, preventing the simplification of intermediate steps by combining them. We present a new activation function that a...
更多查看译文
关键词
Graphics,Geometry,Costs,Convolution,Neural networks,Convolutional neural networks,Arithmetic
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要