Questions

1. A CNN can only process images. (Yes | No)
2. A kernel is a preset matrix used for convolutions. (Yes | No)
3. Does pooling have a pooling matrix or is it random?
4. The size of the dataset always has to be large. (Yes | No)
5. Finding a dataset is not a problem with all the available image banks on the web. (Yes | No)
6. Once a CNN is built, training it does not take much time. (Yes | No)
7. A trained CNN model applies to only one type of images. (Yes | No)
8. A quadratic loss function is not very efficient compared to a cross-entropy function. (Yes | No)
9. The performance of a deep learning CNN does not a represent a real issue with modern CPUs and GPUs. (Yes | No)