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

Using Neuroevolution combined with Novelty Search to promote behaviouraldiversity is capable of constructing high-performing ensembles forclassification. However, using gradient descent to train evolved architecturesduring the search can be computationally prohibitive. Here we propose a methodto overcome this limitation by using a surrogate model which estimates thebehavioural distance between two neural network architectures required tocalculate the sparseness term in Novelty Search. We demonstrate a speedup of 10times over previous work and significantly improve on previous reported resultson three benchmark datasets from Computer Vision -- CIFAR-10, CIFAR-100, andSVHN. This results from the expanded architecture search space facilitated byusing a surrogate. Our method represents an improved paradigm for implementinghorizontal scaling of learning algorithms by making an explicit search fordiversity considerably more tractable for the same bounded resources.

Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers