MLAILGOct 31, 2012

Temporal Autoencoding Restricted Boltzmann Machine

arXiv:1210.8353v12 citations
Originality Incremental advance
AI Analysis

This work addresses a gap in understanding temporal filters for researchers in deep learning and neuroscience, but appears incremental as it builds on existing temporal algorithms.

The paper tackled the problem of extending learned filters from static images to the temporal domain by training on natural movies, and introduced the Temporal Autoencoding Restricted Boltzmann Machine (TARBM) as a new learning paradigm to investigate this.

Much work has been done refining and characterizing the receptive fields learned by deep learning algorithms. A lot of this work has focused on the development of Gabor-like filters learned when enforcing sparsity constraints on a natural image dataset. Little work however has investigated how these filters might expand to the temporal domain, namely through training on natural movies. Here we investigate exactly this problem in established temporal deep learning algorithms as well as a new learning paradigm suggested here, the Temporal Autoencoding Restricted Boltzmann Machine (TARBM).

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes