A short quiz on machine learning in computer vision

Adrian F. Clark

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

   • back propagation

   • forward propagation
   • sideways propagation
   • back and forward propoagation

   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.

2. What is an activation function in a neural network?

   • a linear function
   • a non-linear function
   • a function that weights an input to a neuron

   • a function that converts the sum of the weighted inputs to an output

   An activation function converts the weighted inputs to a neuron into an output. It is usually non-linear, though it doesn't have to be in principle.

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

   • WISARD
   • CNN

   • k-means

   • k-nn

   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.

4. What is transfer learning?

   • adapting a network trained on one thing to recognise another

   • Using features from a pre-trained network as input to a ML algorithm

   • transforming the networks inputs to avoid over-fitting
   • the way in which a deep network is trained

   As deep networks take so long to train from scratch, people now widely use transfer learning instead. This takes the values from some layers of a pre-trained network and uses them as the inputs to a separate machine learning stage, not necessarily even a neural network. In a very real sense, the deep network is being used as a feature detector.

5. What type of images does WISARD need?

   • colour images
   • floating point images

   • binary images containing only the values zero and unity

   • 8 bits/pixel images

   WISARD uses a single bit from each image location to set or clear a bit in its register so it requires binary images. The diagram in figure 10.2 of the lecture notes makes this clear.

6. At its simplest, WISARD consists of:

   • image sampling, a register, some RAM

   • a shift register and some RAM
   • image sampling, some RAM
   • some RAM

   WISARD works by sampling points in an image, storing zero or unity in corresponding points of a register, and then using that register to index into some RAM. The diagram in figure 10.2 of the lecture notes makes this clear.

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

   • it applies the activation function
   • it applies the convolution coefficients to an image

   • it down-samples regions of its input

   • it determines the final result

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

8. What is genetic programming?

   • the use of a genetic algorithm to 'write' a program

   • the execution of parse trees
   • a program that processes genetic data
   • a program that implements a genetic algorithm

   Genetic programming is the use of a genetic algorithm to 'write' programs. It combines program fragments in the form of parse trees into these programs, which it evaluates by running them.

9. In Genetic Programming, programs are commonly presented in which language?

   • Python
   • Java

   • Lisp

   • English

   Programs in GP are normally presented as Lisp. In fact, in the author's GP system, programs are converted to Lisp and executed in that form: the overhead of doing this is tiny.

10. k-means works by:

    • assigning data points to clusters and performing PCA on them

    • alternating between assigning data points to clusters and finding centroids

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

    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!