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

Deep learning has become a popular trend in recent years in the machinelearning community and has even occasionally become synonymous with machinelearning itself thanks to its efficiency, malleability, and ability to operatefree of human intervention. However, a series of hyperparameters passed to aconventional neural network (CoNN) may be rather arbitrary, especially if thereis no surefire way to decide how to program hyperparameters for a givendataset. The random hivemind (RH) alleviates this concern by having multipleneural network estimators make decisions based on random permutations offeatures. The learning rate and the number of epochs may be boosted orattenuated depending on how all features of a given estimator determine theclass that the numerical feature data belong to, but all other hyperparametersremain the same across estimators. This allows one to quickly see whetherconsistent decisions on a given dataset can be made by multiple neural networkswith the same hyperparameters, with random subsets of data chosen to forcevariation in how data are predicted by each, placing the quality of the dataand hyperparameters into focus. The effectiveness of RH is demonstrated throughexperimentation in the predictions of dangerous solar energetic particle events(SEPs) by comparing it to that of using both CoNN and the traditional approachused by ensemble deep learning in this application. Our results demonstratethat RH outperforms the CoNN and a committee-based approach, and demonstratespromising results with respect to the ``all-clear'' prediction of SEPs.

The Random Hivemind: An Ensemble Deep Learner. A Case Study of Application to Solar Energetic Particle Prediction Problem