Neural Networks: Notes and Matlab Code
- Review Questions, Exam 1
- Review Solutions
- Iris Data
- 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".
- Taxonomy Data ( tax001.dat ) This is
just a text array of data. Use the load command (like you did
for the iris data).
- Plot routine: plotcell.m
Useage: once the network "net" is trained using data set X,
and assuming you have run labels.m (above), then:
PROJECT ONE: MUSHROOM CLASSIFICATION
- 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
- Matlab file containing the alphabet
(as a 35 x 26 matrix) Right click with your mouse, and select
"Save Link As..."
- 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.
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!