A memory enhanced LSTM for modeling complex temporal dependencies

TL;DR

Gamma-LSTM introduces a hierarchical memory unit with gating mechanisms, enabling better modeling of complex temporal dependencies and improving performance on tasks involving long sequences.

Contribution

The paper proposes Gamma-LSTM, an enhanced LSTM with hierarchical memory and gating, allowing for multi-level temporal abstraction and improved sequence modeling.

Findings

Outperforms standard LSTMs on pixel-by-pixel MNIST classification

Achieves better generalization on long sequences in natural language inference

Demonstrates effectiveness of hierarchical memory in sequence tasks

Abstract

In this paper, we present Gamma-LSTM, an enhanced long short term memory (LSTM) unit, to enable learning of hierarchical representations through multiple stages of temporal abstractions. Gamma memory, a hierarchical memory unit, forms the central memory of Gamma-LSTM with gates to regulate the information flow into various levels of hierarchy, thus providing the unit with a control to pick the appropriate level of hierarchy to process the input at a given instant of time. We demonstrate better performance of Gamma-LSTM model regular and stacked LSTMs in two settings (pixel-by-pixel MNIST digit classification and natural language inference) placing emphasis on the ability to generalize over long sequences.