# STCN: Stochastic Temporal Convolutional Networks

## TL;DR

STCNs introduce a hierarchical stochastic convolutional architecture that enhances sequence modeling by capturing multi-scale temporal dependencies, achieving state-of-the-art results and high-quality long-range predictions.

## Contribution

The paper presents a novel stochastic temporal convolutional network architecture combining TCNs with hierarchical stochastic latent variables for improved sequence modeling.

## Key findings

- Achieves state-of-the-art log-likelihoods on multiple tasks.
- Capable of generating high-quality long-range synthetic sequences.
- Demonstrates robustness and flexibility due to modular design.

## Abstract

Convolutional architectures have recently been shown to be competitive on many sequence modelling tasks when compared to the de-facto standard of recurrent neural networks (RNNs), while providing computational and modeling advantages due to inherent parallelism. However, currently there remains a performance gap to more expressive stochastic RNN variants, especially those with several layers of dependent random variables. In this work, we propose stochastic temporal convolutional networks (STCNs), a novel architecture that combines the computational advantages of temporal convolutional networks (TCN) with the representational power and robustness of stochastic latent spaces. In particular, we propose a hierarchy of stochastic latent variables that captures temporal dependencies at different time-scales. The architecture is modular and flexible due to the decoupling of the deterministic and stochastic layers. We show that the proposed architecture achieves state of the art log-likelihoods across several tasks. Finally, the model is capable of predicting high-quality synthetic samples over a long-range temporal horizon in modeling of handwritten text.