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

no code implementations • 9 Jan 2018 • Artit Wangperawong, Kettip Kriangchaivech, Austin Lanari, Supui Lam, Panthong Wangperawong

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.