A short quiz on machine learning in computer vision

Adrian F. Clark

1. What is the general strategy of a GA?

   • the best chromosomes 'reproduce' randomly

   • the worst chromosomes 'reproduce' randomly
   • all chromosomes 'reproduce' randomly
   • evolution proceeds by mutation alone

   In a GA, the best chromosomes (those with the lowest costs) 'reproduce' to produce the next generation. It is common to mutate a small number of these 'children' randomly, and to copy some of the best parents from one generation to another. Some forms of GA do permit only mutation by these converge on a solution much more slowly than others.

2. k-means works by:

   • assigning data points to clusters and performing PCA on them
   • assigning data points to clusters and using a MLP on them
   • assigning data points to clusters and using SVM on them

   • alternating between assigning data points to clusters and finding centroids

   k-means is iterative, alternating between assigning points to clusters based on their curent centroids and then finding the centroids of the clusters. The other answers might actually work better but they aren't k-means!

3. Why might one "polish" the result of a genetic algorithm?

   • because a numerical optimizer is too inaccurate

   • to improve the accuracy of the solution

   • because the GA gives its result in the wrong coordinate system
   • because the GA gives the wrong result

   A GA is excellent at exploring the breadth of a search space and finding an approximate solution but it is less effective at determining the exact solution. Using the GA's result to initialize a numerical optimizer, which is what "polishing" means here, combines the best of both algorithms.

4. How goes a real-valued genetic algorithm work?

   • it interpolates along lines in parameter space by a random amount

   • it repeatedly sets parameters to random values
   • it adds together randomly-chosen parameters
   • it multiplies together randomly-chosen parameters

   Real-valued GAs work by choosing two 'genes' randomly to give two points in parameter space, then interpolating along the line joining them by a random amount.

5. How does a GA measure effectiveness on a problem?

   • it uses a cost function to measure the effectiveness of all chromosome

   • it uses crossover to measure effectiveness
   • it uses mutation to measure effectiveness
   • it uses a cost function to measure the effectiveness of one chromosome

   A result is computed for each chromosome (set of values) and the ones closest to the correct solution -- the one with the lowest cost -- are better.

6. What is the purpose of the POOL layer in a CNN?

   • it applies the convolution coefficients to an image
   • it applies the activation function
   • it determines the final result

   • it down-samples regions of its input

   The POOL layer reduces the size of its inputs, usually by down-sampling but sometimes by averaging.

7. What is the most common training techinque for a neural network?

   • forward propagation

   • back propagation

   • back and forward propoagation
   • sideways propagation

   The most widely-used training technique is called back-propagation. It is a way of adjusting the weights of each neuron to reduce the size of the error when evaluating inputs.

8. Which of the following is an unsupervised learning technique?

   • WISARD

   • k-means

   • k-nn
   • CNN

   k-means is unsupervised, while both WISARD and CNN are supervised learning techniques. k-NN isn't really a machine learning technique, more a way of matching things for similarity.

9. What is over-training in neural networks?

   • where the network recognizes specific patterns and does not generalize

   • where the network recognizes only general patterns
   • where the number of training epochs is too large
   • where the network fails to converge

   Over-training is when the neural network 'learns' each input pattern but is unable to classify correctly similar patterns: it has 'forgotten' the general pattern by focussing on the specific training ones.

10. What is the purpose of the RELU layer in a CNN?

    • it applies the convolution coefficients to an image
    • it down-samples regions of its input
    • it determines the final result

    • it applies the activation function

    The RELU layer applies the activation function to each element independently.