Skip to main content
. Author manuscript; available in PMC: 2019 Sep 1.
Published in final edited form as: IEEE Trans Biomed Eng. 2017 Jun 15;65(9):1975–1984. doi: 10.1109/TBME.2017.2715281

Fig. 5.

Fig. 5.

Visualization of the trained RSNs-specific filters for convolutional layer 2. This layer also contains 32 different types of filters, each of which has a size of 3*3*3*32 (32 input channels for this layers). Here, only the filters for the first channel of all the 32 are shown, with entire filters and clipped filters separated by a dashed line in the middle in each panel.