2022

CogPonder

Add human-like response time to deep learning models

AI/ML/Data
Cognitive
Uni.lu

2022

Inspired by the Test-Operate-Test-Exit (TOTE) and the PonderNet frameworks, CogPonder functionally decouples the act of control from the controlled act by introducing a controller that wraps around any end-to-end deep learning model and decides when to terminate processing and output a response, producing both a response and response time.