@Misc{SousaFernVasc:2021:NoSeNe,
author = "Sousa, Eduardo Vera and Fernandes, Leandro A. F. and Vasconcelos,
Cristina Nader",
title = "ConformalLayers: A non-linear sequential neural network with
associative layers",
year = "2021",
date = "18-22 Oct. 2021",
keywords = "convolutional neural network, non-linear activation,
associativity.",
targetfile = "SupplementaryMaterial.pdf",
abstract = "Convolutional Neural Networks (CNNs) have been widely applied. But
as the CNNs grow, the number of arithmetic operations and memory
footprint also increases. 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 allows associativity between sequential layers of
CNNs. Even though our activation function is non-linear, it can be
represented by a sequence of linear operations in the conformal
model for Euclidean geometry. In this domain, operations like, but
not limited to, convolution, average pooling, and dropout remain
linear. We take advantage of associativity to combine all the
{"}conformal layers{"} and make the cost of inference constant
regardless of the depth of the network.",
affiliation = "{Universidade Federal Fluminense} and {Universidade Federal
Fluminense} and {Universidade Federal Fluminense}",
language = "en",
ibi = "8JMKD3MGPEW34M/45CGCRL",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CGCRL",
urlaccessdate = "2024, May 19"
}