Convolutional Neural Network
Convolutional neural network (CNN) gains great success on
Euclidean data, e.g., image, text, audio, and video
Image classification, object detection, machine translation
The power of CNN lies in
its ability to learn local stationary structures, via localized
convolution filter, and compose them to form multi-scale
hierarchical patterns
2
M. M. Bronstein, J. Bruna, Y. LeCun, A. Szlam, P. Vandergheynst. Geometric deep learning: going beyond Euclidean
data. IEEE Signal Processing Magazine, 18-42, 2017.
Temporal convolutional networkConvolutional neural networks on image
评论0