Generalised Structural CNNs (SCNNs) for time series data with arbitrary graph topology

T Teh, C Auepanwiriyakul, JA Harston… - arXiv preprint arXiv …, 2018 - arxiv.org
Deep Learning methods, specifically convolutional neural networks (CNNs), have seen a lot
of success in the domain of image-based data, where the data offers a clearly structured
topology in the regular lattice of pixels. This 4-neighbourhood topological simplicity makes
the application of convolutional masks straightforward for time series data, such as video
applications, but many high-dimensional time series data are not organised in regular
lattices, and instead values may have adjacency relationships with non-trivial topologies …

[PDF][PDF] Generalised Structural CNNs (SCNNs) for time series data with arbitrary graph-toplogies

T Teh, C Auepanwiriyakul, JA Harston… - arXiv preprint arXiv …, 2018 - core.ac.uk
Deep Learning methods, specifically convolutional neural networks (CNNs), have seen a lot
of success in the domain of image-based data, where the data offers a clearly structured
topology in the regular lattice of pixels. This 4-neighbourhood topological simplicity makes
the application of convolutional masks straightforward for time series data, such as video
applications, but many high-dimensional time series data are not organised in regular
lattices, and instead values may have adjacency relationships with non-trivial topologies …
以上显示的是最相近的搜索结果。 查看全部搜索结果