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

Machine learning (ML) classifiers always benefit from more informative inputfeatures. We seek to auto-generate stronger feature sets in order to addressthe difficulty that ML methods often experience given limited training data. Awide range of biological neural nets (BNNs) excel at fast learning, implyingthat they are adept at extracting informative features. We can thus look toBNNs for tools to improve ML performance in this low-data regime. The insectolfactory network learns new odors very rapidly, by means of three keyelements: A competitive inhibition layer; a high-dimensional sparse plasticlayer; and Hebbian updates of synaptic weights.  In this work, we deployed MothNet, a computational model of the insectolfactory network, as an automatic feature generator: Attached as a front-endpre-processor, its Readout Neurons provided new features, derived from theoriginal features, for use by standard ML classifiers. We found that these"insect cyborgs", i.e. classifiers that are part-insect model and part-MLmethod, had significantly better performance than baseline ML methods alone ona vectorized MNIST dataset. The MothNet feature generator also substantiallyout-performed other feature generating methods such as PCA, PLS, and NNs, aswell as pre-training to initialize NN weights. Cyborgs improved relative testset accuracy by an average of 6% to 33% depending on baseline ML accuracy,while relative reduction in test set error exceeded 50% for higher baselineaccuracy ML models. These results indicate the potential value of BNN-inspiredfeature generators in the ML context.

Insect cyborgs: Bio-mimetic feature generators improve machine learning accuracy on limited data