arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1803.03067cs.AI
收藏

用于机器推理的组合注意力网络

Compositional Attention Networks for Machine Reasoning

Stanford University(斯坦福大学)

Drew A. Hudson, Christopher D. Manning

摘要:

我们提出了MAC网络,一种新的完全可微的神经网络架构,旨在促进明确和表达的推理。MAC从单一的黑盒神经架构转向鼓励透明性和多功能性的设计。该模型通过将问题分解为一系列基于注意力的推理步骤来解决问题,每个步骤都由一个新的循环记忆,注意力和组合(MAC)单元执行,该单元保持控制和记忆之间的分离。通过将细胞串在一起并施加调节其相互作用的结构约束,MAC有效地学习执行直接从端到端方法中的数据推断的迭代推理过程。我们在具有挑战性的CLEVR数据集上展示了该模型的强度、鲁棒性和可解释性,实现了最新的98.9%的准确率,将之前最佳模型的出错率减半。更重要的是,我们证明了该模型具有计算效率和数据效率,特别是需要比现有模型少5倍的数据才能获得强大的结果。

英文摘要:

We present the MAC network, a novel fully differentiable neural network architecture, designed to facilitate explicit and expressive reasoning. MAC moves away from monolithic black-box neural architectures towards a design that encourages both transparency and versatility. The model approaches problems by decomposing them into a series of attention-based reasoning steps, each performed by a novel recurrent Memory, Attention, and Composition (MAC) cell that maintains a separation between control and memory. By stringing the cells together and imposing structural constraints that regulate their interaction, MAC effectively learns to perform iterative reasoning processes that are directly inferred from the data in an end-to-end approach. We demonstrate the model's strength, robustness and interpretability on the challenging CLEVR dataset for visual reasoning, achieving a new state-of-the-art 98.9% accuracy, halving the error rate of the previous best model. More importantly, we show that the model is computationally-efficient and data-efficient, in particular requiring 5x less data than existing models to achieve strong results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑