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

This paper examines three generic strategies for improving the performance ofneuro-evolution techniques aimed at evolving convolutional neural networks(CNNs). These were implemented as part of the Evolutionary eXploration ofAugmenting Convolutional Topologies (EXACT) algorithm. EXACT evolves arbitraryconvolutional neural networks (CNNs) with goals of better discovering andunderstanding new effective architectures of CNNs for machine learning tasksand to potentially automate the process of network design and selection. Thestrategies examined are node-level mutation operations, epigenetic weightinitialization and pooling connections. Results were gathered over the periodof a month using a volunteer computing project, where over 225,000 CNNs weretrained and evaluated across 16 different EXACT searches. The node mutationoperations where shown to dramatically improve evolution rates over traditionaledge mutation operations (as used by the NEAT algorithm), and epigenetic weightinitialization was shown to further increase the accuracy and generalizabilityof the trained CNNs. As a negative but interesting result, allowing for poolingconnections was shown to degrade the evolution progress. The best trained CNNsreached 99.46% accuracy on the MNIST test data in under 13,500 CNN evaluations-- accuracy comparable with some of the best human designed CNNs.

Accelerating the Evolution of Convolutional Neural Networks with Node-Level Mutations and Epigenetic Weight Initialization