papers AI Learner
The Github is limit! Click to go to the new site.

Contextual Memory Trees

2019-02-14
Wen Sun, Alina Beygelzimer, Hal Daumé III, John Langford, Paul Mineiro

Abstract

We design and study a Contextual Memory Tree (CMT), a learning memory controller that inserts new memories into an experience store of unbounded size. It is designed to efficiently query for memories from that store, supporting logarithmic time insertion and retrieval operations. Hence CMT can be integrated into existing statistical learning algorithms as an augmented memory unit without substantially increasing training and inference computation. Furthermore CMT operates as a reduction to classification, allowing it to benefit from advances in representation or architecture. We demonstrate the efficacy of CMT by augmenting existing multi-class and multi-label classification algorithms with CMT and observe statistical improvement. We also test CMT learning on several image-captioning tasks to demonstrate that it performs computationally better than a simple nearest neighbors memory system while benefitting from reward learning.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1807.06473

PDF

https://arxiv.org/pdf/1807.06473


Similar Posts

Comments