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

We consider the problem of learning a neural network classifier. Under theinformation bottleneck (IB) principle, we associate with this classificationproblem a representation learning problem, which we call "IB learning". We showthat IB learning is, in fact, equivalent to a special class of the quantizationproblem. The classical results in rate-distortion theory then suggest that IBlearning can benefit from a "vector quantization" approach, namely,simultaneously learning the representations of multiple input objects. Such anapproach assisted with some variational techniques, result in a novel learningframework, "Aggregated Learning", for classification with neural networkmodels. In this framework, several objects are jointly classified by a singleneural network. The effectiveness of this framework is verified throughextensive experiments on standard image recognition and text classificationtasks.

Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network Classifiers