In this paper, we study the size and width of autoencoders consisting of Boolean threshold functions, where an autoencoder is a layered neural network whose structure can be viewed as consisting of an encoder, which compresses an input vector to a lower dimensional vector, and a decoder which transforms the low-dimensional vector back to the original input vector exactly (or approximately). We focus on the decoder part, and show that $\Omega(\sqrt{Dn/d})$ and $O(\sqrt{Dn})$ nodes are required to transform $n$ vectors in $d$-dimensional binary space to $D$-dimensional binary space. We also show that the width can be reduced if we allow small errors, where the error is defined as the average of the Hamming distance between each vector input to the encoder part and the resulting vector output by the decoder.
翻译:在本文中,我们研究了由布林阈值功能组成的自动解码器的大小和宽度,其中自动解码器是一个分层神经网络,其结构可被视为包括一个编码器,该编码器将输入矢量压缩到一个低维矢量,以及一个解码器将低维矢量转换回原输入矢量的精确(或大约)。我们集中关注解码器部分,并显示,将美元/O(sqrt{Dn})美元和美元/O(sqrt{Dn})元节点用于将美元维维的二元空间的一元矢量转换到美元维的二元空间。我们还显示,如果我们允许小错误,则宽度可以缩小,错误被定义为向编码器部分的每种矢量输入之间的恒定距离平均值,以及解码器产生的矢量输出值。