English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Autoencoders are a type of unsupervised neural networks, which can be used tosolve various tasks, e.g., dimensionality reduction, image compression, andimage denoising. An AE has two goals: (i) compress the original input to alow-dimensional space at the bottleneck of the network topology using anencoder, (ii) reconstruct the input from the representation at the bottleneckusing a decoder. Both encoder and decoder are optimized jointly by minimizing adistortion-based loss which implicitly forces the model to keep only thosevariations of input data that are required to reconstruct the and to reduceredundancies. In this paper, we propose a scheme to explicitly penalize featureredundancies in the bottleneck representation. To this end, we propose anadditional loss term, based on the pair-wise correlation of the neurons, whichcomplements the standard reconstruction loss forcing the encoder to learn amore diverse and richer representation of the input. We tested our approachacross different tasks: dimensionality reduction using three different dataset,image compression using the MNIST dataset, and image denoising using fashionMNIST. The experimental results show that the proposed loss leads consistentlyto superior performance compared to the standard AE loss.

Reducing Redundancy in the Bottleneck Representation of the Autoencoders