Dynamic Adaptive Network Intelligence
This addresses the challenge of accurate representational learning for machines to perform complex reasoning, with incremental improvements in a specific domain.
The paper tackles the problem of learning explicit and implicit relationships in data for complex reasoning by introducing the Dynamic Adaptive Network Intelligence (DANI) model, achieving state-of-the-art results on difficult question answering tasks in the bAbI dataset.
Accurate representational learning of both the explicit and implicit relationships within data is critical to the ability of machines to perform more complex and abstract reasoning tasks. We describe the efficient weakly supervised learning of such inferences by our Dynamic Adaptive Network Intelligence (DANI) model. We report state-of-the-art results for DANI over question answering tasks in the bAbI dataset that have proved difficult for contemporary approaches to learning representation (Weston et al., 2015).