The goal of this assignment is to implement a
multi-layer neural network model.
To begin this assignment download
theKamangar_01.zip and unzip it in your
computer.
The neural network model in this assignment is a multi-layer of
neurons with multiple nodes in each layer.
The activation (transfer) function of all the nodes is assumed to
be a sigmoid function.
Your model weightsshould
include the bias(es).
Your code should be vectorized using numpy.DO
NOT use any other package or library (other
than numpy).
DO NOT alter/change the name of the function or
the parameters of the function. You may introduce additional
functions (helper functions) as needed. All the helper functions
should be put in the same file with multi_layer_nn()
function
The comments in
themulti_layer_nn() function provide
additional information that should help with your
implementation.
The Assignment_01_tests.py file includes a very minimal set of unit
tests for the multi_layer_nn.py file. The assignment grade will be
based on your code passing these tests (and other additional
tests).
You may modify the "Assignment_01_tests.py" to include more tests. You may also add
additional tests to help you duringdevelopment of your
code.
DO NOTsubmit the test
files file when submitting your Assignment_01
DO NOT submit the
python environment files (if you used an environment for your
project)
You may run these tests using the command:
py.test --verbose
Assignment_01_tests.py
The following is roughly what your output should
look like if all tests pass