Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks

We propose a novel memory cell for recurrent neural networks that dynamically maintains information across long windows of time using relatively few resources. The Legendre Memory Unit~(LMU) is mathematically derived to orthogonalize its continuous-time history -- doing so by solving $d$ coupled ordinary differential equations~(ODEs), whose phase space linearly maps onto sliding windows of time via the Legendre polynomials up to degree $d - 1$... (read more)

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Sequential Image Classification Sequential MNIST LMU Permuted Accuracy 97.2% # 4

Methods used in the Paper


METHOD TYPE
LMU
Recurrent Neural Networks