Deep Autoencoder Model Construction Based on Pytorch

TL;DR

This paper introduces a deep autoencoder built with Pytorch that employs random weight clearing to induce sparsity, effectively reducing overfitting and enhancing image classification accuracy.

Contribution

It presents a novel Pytorch-based deep autoencoder with a sparsity-inducing method that improves classification performance over existing models.

Findings

Improved image classification accuracy.

Effective reduction of overfitting.

Outperforms ELM, RELM, AE, SAE, DAE in experiments.

Abstract

This paper proposes a deep autoencoder model based on Pytorch. This algorithm introduces the idea of Pytorch into the auto-encoder, and randomly clears the input weights connected to the hidden layer neurons with a certain probability, so as to achieve the effect of sparse network, which is similar to the starting point of the sparse auto-encoder. The new algorithm effectively solves the problem of possible overfitting of the model and improves the accuracy of image classification. Finally, the experiment is carried out, and the experimental results are compared with ELM, RELM, AE, SAE, DAE.