---

Week 9: Journal Questions

 Answer the following question for Monday's reading about convolution and deep learning (Mitchell Chapter 4)

1. Looking at the photo shown above, write several sentences about what you can infer about what is taking place in the photo.
2. Based on the reading, what might a convolutional, deep neural network be able to infer about this same photo?
3. At the top of page 75, 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)

1. What is ImageNet and what role did it play in the emergence of deep learning?
2. On page 88, 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.