Consider a CNN that takes in 32 × 32 grayscale images and has a single convolution layer with three 5 × 5 convolution fi
Posted: Fri May 20, 2022 6:12 pm
Consider a CNN that takes in 32 × 32 grayscale images and has a
single convolution layer with three 5 × 5 convolution filters
(without boundary padding).
(a) Draw a sketch of the input and first hidden layer similar to
Figure 10.8.
(b) How many parameters are in this model?
(c) Explain how this model can be thought of as an ordinary
feedforward neural network with the individual pixels as inputs,
and with constraints on the weights in the hidden units. What are
the constraints? (d) If there were no constraints, then how many
weights would there be in the ordinary feed-forward neural network
in (c)?
16 32 8 32 16 32 500 100 2. pool pool convolve pool convolve flatten convolve
single convolution layer with three 5 × 5 convolution filters
(without boundary padding).
(a) Draw a sketch of the input and first hidden layer similar to
Figure 10.8.
- Consider A Cnn That Takes In 32 32 Grayscale Images And Has A Single Convolution Layer With Three 5 5 Convolution Fi 1 (201.91 KiB) Viewed 70 times
(c) Explain how this model can be thought of as an ordinary
feedforward neural network with the individual pixels as inputs,
and with constraints on the weights in the hidden units. What are
the constraints? (d) If there were no constraints, then how many
weights would there be in the ordinary feed-forward neural network
in (c)?
16 32 8 32 16 32 500 100 2. pool pool convolve pool convolve flatten convolve