Neural Networks: Notes and Matlab Code




  1. Review Questions, Exam 1
  2. Review Solutions

  1. Iris Data

  1. Labels for Data below (labels.m) When you run labels.m, you will create a cell structure with names (this is actually a short script file). The names will be stored in "G".
  2. Taxonomy Data ( tax001.dat ) This is just a text array of data. Use the load command (like you did for the iris data).
  3. Plot routine: plotcell.m
    Useage: once the network "net" is trained using data set X, and assuming you have run labels.m (above), then:
    plotcell(net,X,G)

PROJECT ONE: MUSHROOM CLASSIFICATION
  1. Mushroom data as a Matlab file. Both the inputs (matrix X) and the targets (vector Y) are included. Right click with your mouse, and select "Save Link As..."

PROJECT TWO: ALPHABET RECOGNITION
  1. Matlab file containing the alphabet (as a 35 x 26 matrix) Right click with your mouse, and select "Save Link As..."
  2. Function to map a 35-dimensional vector back to a 5 x 7 grid (to see what the letters look like!)

Links to Data For Projects:

Time Series Library For time series, you would be working with the prediction problem: Given k values of the past, predict the current (and perhaps the next) value of the series. See me for more details.
Machine Learning Repository Most of these problems will be classification problems- either unsupervised (by clustering) or supervised (via neural nets). Lots of data here! There are data sets that are probably not appropriate for the project- be sure to clear your idea with me!