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 Ne
本研究提出了一种名为 DEN (Dynamically Expandable Network) 的深度网络架构,可以在学习一系列任务时动态决定其网络容量,从而学习任务之间的重叠知识共享结构,通过选择性重新训练、动态扩展网络容量和时间戳来有效地防止语义漂移,并在现有公共数据集中验证了 DEN 的有效性。