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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper presents a novel Generative Neural Network Architecture formodelling the inverse function of an Artificial Neural Network (ANN) eithercompletely or partially. Modelling the complete inverse function of an ANNinvolves generating the values of all features that corresponds to a desiredoutput. On the other hand, partially modelling the inverse function meansgenerating the values of a subset of features and fixing the remaining featurevalues. The feature set generation is a critical step for artificial neuralnetworks, useful in several practical applications in engineering and science.The proposed Oracle Guided Generative Neural Network, dubbed as OGGN, isflexible to handle a variety of feature generation problems. In general, an ANNis able to predict the target values based on given feature vectors. The OGGNarchitecture enables to generate feature vectors given the predetermined targetvalues of an ANN. When generated feature vectors are fed to the forward ANN,the target value predicted by ANN will be close to the predetermined targetvalues. Therefore, the OGGN architecture is able to map, inverse function ofthe function represented by forward ANN. Besides, there is another importantcontribution of this work. This paper also introduces a new class of functions,defined as constraint functions. The constraint functions enable a neuralnetwork to investigate a given local space for a longer period of time. Thus,enabling to find a local optimum of the loss function apart from just beingable to find the global optimum. OGGN can also be adapted to solve a system ofpolynomial equations in many variables. The experiments on synthetic datasetsvalidate the effectiveness of OGGN on various use cases.

OGGN: A Novel Generalized Oracle Guided Generative Architecture for Modelling Inverse Function of Artificial Neural Networks