• What is a "feature"?
• Write out the convolutional kernel matrix for a top edge detector.
• Write out the mathematical operation applied by a 3×3 kernel to a single pixel in an image.
• What is the value of a convolutional kernel apply to a 3×3 matrix of zeros?
• What is "padding"?
• What is "stride"?
• Create a nested list comprehension to complete any task that you choose.
• What are the shapes of the input and weight parameters to PyTorch's 2D convolution?
• What is a "channel"?
• What is the relationship between a convolution and a matrix multiplication?
• What is a "convolutional neural network"?
• What is the benefit of refactoring parts of your neural network definition?
• What is Flatten? Where does it need to be included in the MNIST CNN? Why?
• What does "NCHW" mean?
• Why does the third layer of the MNIST CNN have 7*7*(1168-16) multiplications?
• What is a "receptive field"?
• What is the size of the receptive field of an activation after two stride 2 convolutions? Why?
• Run conv-example.xlsx yourself and experiment with trace precedents.
• Have a look at Jeremy or Sylvain's list of recent Twitter "like"s, and see if you find any interesting resources or ideas there.
• How is a color image represented as a tensor?