Autoencoder has been widely used as a feature learning technique. In many works of autoencoder, the features of the original input are usually extracted layer by layer using multi-layer nonlinear mapping, and only the features of the last layer are used for classification or regression. Therefore, the features of the previous layer aren’t used explicitly. The loss of information and waste of computation is obvious. In addition, faster training and reasoning speed is generally required in the Internet of Things applications. But the stacked autoencoders model is usually trained by the BP algorithm, which has the problem of slow convergence. To solve the above two problems, the paper proposes a dense connection pseudoinverse learning autoencoder (DensePILAE) from reuse perspective. Pseudoinverse learning autoencoder (PILAE) can extract features in the form of analytic solution, without multiple iterations. Therefore, the time cost can be greatly reduced. At the same time, the features of all the previous layers in stacked PILAE are combined as the input of next layer. In this way, the information of all the previous layers not only has no loss, but also can be strengthened and refined, so that better features could be learned. The experimental results in 8 data sets of different domains show that the proposed DensePILAE is effective.

自编码器已被广泛用作特征学习技术。在许多自编码器的工作中，通常使用多层非线性映射逐层提取原始输入的特征，仅将最后一层的特征用于分类或回归。因此，没有明确使用前一层的特征。信息的丢失和计算的浪费是显而易见的。此外，物联网应用一般要求更快的训练和推理速度。但是stacked autoencoders模型通常是用BP算法训练的，存在收敛慢的问题。针对以上两个问题，论文从复用的角度提出了一种密集连接伪逆学习自编码器（DensePILAE）。伪逆学习自编码器（PILAE）可以以解析解的形式提取特征，无需多次迭代。因此，可以大大降低时间成本。同时，将堆叠的 PILAE 中所有前一层的特征组合起来作为下一层的输入。这样，前面所有层的信息不仅没有损失，而且可以得到加强和细化，从而可以学习到更好的特征。在不同领域的 8 个数据集上的实验结果表明，所提出的 DensePILAE 是有效的。前面所有层的信息不仅没有损失，而且可以加强和细化，从而可以学习到更好的特征。在不同领域的 8 个数据集上的实验结果表明，所提出的 DensePILAE 是有效的。前面所有层的信息不仅没有损失，而且可以加强和细化，从而可以学习到更好的特征。在不同领域的 8 个数据集上的实验结果表明，所提出的 DensePILAE 是有效的。