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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Learning deep representations to solve complex machine learning tasks hasbecome the prominent trend in the past few years. Indeed, Deep Neural Networksare now the golden standard in domains as various as computer vision, naturallanguage processing or even playing combinatorial games. However, problematiclimitations are hidden behind this surprising universal capability. Among otherthings, explainability of the decisions is a major concern, especially sincedeep neural networks are made up of a very large number of trainableparameters. Moreover, computational complexity can quickly become a problem,especially in contexts constrained by real time or limited resources.Therefore, understanding how information is stored and the impact this storagecan have on the system remains a major and open issue. In this chapter, weintroduce a method to transform deep neural network models into deepassociative memories, with simpler, more explicable and less expensiveoperations. We show through experiments that these transformations can be donewithout penalty on predictive performance. The resulting deep associativememories are excellent candidates for artificial intelligence that is easier totheorize and manipulate.

DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning Problems