Regularized Dynamic Boltzmann Machine with Delay Pruning for Unsupervised Learning of Temporal Sequences

TL;DR

This paper introduces Delay Pruning, a regularization technique for dynamic Boltzmann machines (DyBM), improving their ability to learn complex temporal sequences by pruning FIFO queue delays, with demonstrated success on high-dimensional data.

Contribution

The paper proposes Delay Pruning, a novel regularization method for DyBM that enhances learning of temporal sequences by optimizing FIFO queue delays.

Findings

Delay Pruning improves DyBM's sequence learning performance.

Delay Pruning outperforms Dropout and DropConnect in experiments.

DyBM with Delay Pruning effectively learns high-dimensional sequences.

Abstract

We introduce Delay Pruning, a simple yet powerful technique to regularize dynamic Boltzmann machines (DyBM). The recently introduced DyBM provides a particularly structured Boltzmann machine, as a generative model of a multi-dimensional time-series. This Boltzmann machine can have infinitely many layers of units but allows exact inference and learning based on its biologically motivated structure. DyBM uses the idea of conduction delays in the form of fixed length first-in first-out (FIFO) queues, with a neuron connected to another via this FIFO queue, and spikes from a pre-synaptic neuron travel along the queue to the post-synaptic neuron with a constant period of delay. Here, we present Delay Pruning as a mechanism to prune the lengths of the FIFO queues (making them zero) by setting some delay lengths to one with a fixed probability, and finally selecting the best performing model with fixed delays. The uniqueness of structure and a non-sampling based learning rule in DyBM, make the application of previously proposed regularization techniques like Dropout or DropConnect difficult, leading to poor generalization. First, we evaluate the performance of Delay Pruning to let DyBM learn a multidimensional temporal sequence generated by a Markov chain. Finally, we show the effectiveness of delay pruning in learning high dimensional sequences using the moving MNIST dataset, and compare it with Dropout and DropConnect methods.