Posts by Daniel Möller • 111 points
2 posts
-
0
votes2
answers48
viewsA: multivariate regression in Keras
The complex mathematics of neural networks can create confusion in the model. If this input does not significantly contribute to a better result, it may be that it disrupts and "consumes" part of…
-
1
votes1
answer119
viewsA: Convolution 1D Keras
Convolutions always need two extra dimensions, one for "samples" (samples in your "batch") and one for channels (Channels). Therefore, 1D convolutions need 3 dimensions, and 2D convolutions need 4.…