Comparing heterogeneous entities using artificial neural networks of trainable weighted structural components and machine-learned activation functions

TL;DR

This paper introduces a neural network model that compares heterogeneous entities like news articles and videos using trainable structural components and machine-learned activation functions, achieving up to 59.2% accuracy in matching tasks.

Contribution

The paper presents a novel neural network approach with trainable weighted structural components and learned activation functions for cross-entity comparison.

Findings

Achieved 59.2% accuracy in matching videos to news articles.

Developed a mobile app for related video recommendations.

Demonstrated potential for cross-category product cross-selling.

Abstract

To compare entities of differing types and structural components, the artificial neural network paradigm was used to cross-compare structural components between heterogeneous documents. Trainable weighted structural components were input into machine-learned activation functions of the neurons. The model was used for matching news articles and videos, where the inputs and activation functions respectively consisted of term vectors and cosine similarity measures between the weighted structural components. The model was tested with different weights, achieving as high as 59.2% accuracy for matching videos to news articles. A mobile application user interface for recommending related videos for news articles was developed to demonstrate consumer value, including its potential usefulness for cross-selling products from unrelated categories.