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

In the quest towards general artificial intelligence (AI), researchers haveexplored developing loss functions that act as intrinsic motivators in theabsence of external rewards. This paper argues that such research hasoverlooked an important and useful intrinsic motivator: social interaction. Weposit that making an AI agent aware of implicit social feedback from humans canallow for faster learning of more generalizable and useful representations, andcould potentially impact AI safety. We collect social feedback in the form offacial expression reactions to samples from Sketch RNN, an LSTM-basedvariational autoencoder (VAE) designed to produce sketch drawings. We use aLatent Constraints GAN (LC-GAN) to learn from the facial feedback of a smallgroup of viewers, by optimizing the model to produce sketches that it predictswill lead to more positive facial expressions. We show in multiple independentevaluations that the model trained with facial feedback produced sketches thatare more highly rated, and induce significantly more positive facialexpressions. Thus, we establish that implicit social feedback can improve theoutput of a deep learning model.

Learning via social awareness: Improving a deep generative sketching model with facial feedback