Improving Generalization of Sequence Encoder-Decoder Networks for Inverse Imaging of Cardiac Transmembrane Potential

TL;DR

This paper investigates how constrained stochasticity and global temporal aggregation in latent space improve the generalization of sequence encoder-decoder networks for inverse imaging of cardiac transmembrane potential, supported by theoretical and empirical analysis.

Contribution

It introduces a theoretical framework and a novel LSTM-based architecture that enhance generalization in inverse sequence reconstruction tasks.

Findings

Stochastic latent space improves generalization.

Global temporal aggregation enhances reconstruction accuracy.

The proposed model outperforms deterministic counterparts.

Abstract

Deep learning models have shown state-of-the-art performance in many inverse reconstruction problems. However, it is not well understood what properties of the latent representation may improve the generalization ability of the network. Furthermore, limited models have been presented for inverse reconstructions over time sequences. In this paper, we study the generalization ability of a sequence encoder decoder model for solving inverse reconstructions on time sequences. Our central hypothesis is that the generalization ability of the network can be improved by 1) constrained stochasticity and 2) global aggregation of temporal information in the latent space. First, drawing from analytical learning theory, we theoretically show that a stochastic latent space will lead to an improved generalization ability. Second, we consider an LSTM encoder-decoder architecture that compresses a global latent vector from all last-layer units in the LSTM encoder. This model is compared with alternative LSTM encoder-decoder architectures, each in deterministic and stochastic versions. The results demonstrate that the generalization ability of an inverse reconstruction network can be improved by constrained stochasticity combined with global aggregation of temporal information in the latent space.