Journal Questions
 Answer the following question for
Monday's reading about convolution and deep learning (Mitchell Chapters 4)
-
Looking at the photo shown above, write several sentences about what you can infer about what is taking place in the photo.
-
Based on the reading, what might a convolutional, deep neural network be able to infer about this same photo?
-
On page 82, Mitchell writes that "the units in a ConvNet act
as detectors for important visual features, each unit
looking for a its preferred feature in a specific part of
the visual field." How is this different from how a typical
sigmoid unit operates in a standard layered neural network?
 Answer the following question for
Wednesday's reading on ImageNet (Mitchell Chapters 5)
-
What is ImageNet and what role did it play in the emergence of deep learning?
-
On page 95, Mitchell states that "a cardinal rule in machine learning is don't train on the test data." Explain the significance of this rule.
 No journal response needed for Friday.