Question

11.
Which ones of the following statements are true about Inception Networks?
1. A single inception block allows the network to use a combination of 1x1, 3x3,
5x5 convolutions and pooling.
2. Making an inception network deeper (by stacking more inception blocks
together) should not hurt training set performance.
3. Inception blocks usually use 1x1 convolutions to reduce the input data volumes
size before applying 3x3 and 5x5 convolutions.
4. Inception networks incorporates a variety of network architectures (similar to
dropout, which randomly chooses a network architecture on each step) and thus
has a similar regularizing effect as dropout.
A Both 1 and 2
B Both 2 and 3
C Both 1 and 3
D All four
Previous
Next
09:23
(8:
(»)) ENG​

Answer 1

I dont know sorry pls follow