A short quiz on machine learning in computer vision

Adrian F. Clark

At its simplest, WISARD consists of:
- some RAM
- a shift register and some RAM
- image sampling, some RAM
- image sampling, a register, 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.
Which of the following is NOT a well-known deep neural network architecture?
- DNNarch
- GoogLeNet
- AlexNet
- ResNet
AlexNet was the first deep CNN to show real promise, and this was followed by GoogLeNet. ResNet is roughly the state of the art, and RecNet is one I make up!
k-means works by:
- assigning data points to clusters and performing PCA on them
- assigning data points to clusters and using SVM on them
- assigning data points to clusters and using a MLP 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!
How goes a real-valued genetic algorithm work?
- it multiplies together randomly-chosen parameters
- it interpolates along lines in parameter space by a random amount
- it repeatedly sets parameters to random values
- it adds 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.
What is an activation function in a neural network?
- a non-linear function
- a 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.
What is the purpose of the RELU layer in a CNN?
- it applies the activation function
- it determines the final result
- it applies the convolution coefficients to an image
- it down-samples regions of its input
The RELU layer applies the activation function to each element independently.
What type of images does WISARD need?
- floating point images
- 8 bits/pixel images
- colour images
- binary images containing only the values zero and unity
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.
What is transfer learning?
- Using features from a pre-trained network as input to a ML algorithm
- the way in which a deep network is trained
- transforming the networks inputs to avoid over-fitting
- adapting a network trained on one thing to recognise another
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.
What is the purpose of the POOL layer in a CNN?
- it determines the final result
- it applies the convolution coefficients to an image
- it applies the activation function
- it down-samples regions of its input
The POOL layer reduces the size of its inputs, usually by down-sampling but sometimes by averaging.
How does SVM work?
- it finds the hyperplane that maximizes the distance between classes
- it finds the smallest hypersphere that minimises encloses each class
- it finds the hyperplane that minimizes the distance between classes
- it reduces the problem to a linear one and finds the best straight line
SVM maximizes the distance between classes and uses a hyperplane to separate them.