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

The meta learning few-shot classification is an emerging problem in machinelearning that received enormous attention recently, where the goal is to learna model that can quickly adapt to a new task with only a few labeled data. Weconsider the Bayesian Gaussian process (GP) approach, in which we meta-learnthe GP prior, and the adaptation to a new task is carried out by the GPpredictive model from the posterior inference. We adopt the Laplace posteriorapproximation, but to circumvent the iterative gradient steps for finding theMAP solution, we introduce a novel linear discriminant analysis (LDA) plugin asa surrogate for the MAP solution. In essence, the MAP solution is approximatedby the LDA estimate, but to take the GP prior into account, we adopt theprior-norm adjustment to estimate LDA's shared variance parameters, whichensures that the adjusted estimate is consistent with the GP prior. Thisenables closed-form differentiable GP posteriors and predictive distributions,thus allowing fast meta training. We demonstrate considerable improvement overthe previous approaches.

Gaussian Process Meta Few-shot Classifier Learning via Linear Discriminant Laplace Approximation