Legend

MiPj -- Midterm i problem j

Fi -- Final problem i

Each class had distinct versions of all exams. Within a class there were also two versions of a given test; however, these two versions were just problem permutations of each other. The results above are all for the second of these two permutations.

CLO1 -- Be able to code without a library a single perceptron training algorithm.

CLO2 -- Be able to predict the effect of different activation functions on the ability of a network to learn.

CLO3 -- Be able to explain how different neural network training algorithms work.

CLO4 -- Be able to select neural network layers type to build a network suitable for various learning tasks such as object classification, object detection, language processing, planning, policy selection, etc.

CLO5 -- Be able to select an appropriate regularization technique for a given learning task.

CLO6 -- Be able to code and train with a library such as Caffe, Theano, Tensorflow a multi-layer neural network.

CLO7 -- Be able to measure the performance of a model, determine if more data in needed, as well as how to tune the model.

N/A -- Important material covered in the course but not directly related to a specific learning outcome.