Description
(Only NumPy and data visualization packages are allowed.)
1.Read through Slide11 and 12, watch video lectures of neural networks.
2.Run the code “8_NN_2layer.py”(blackboard)
3. Trains the NN more than 1,000 times and observe the change of the loss value.
4. Implement a “3-6-2” network (using code 8_NN_2layer.py) to fit the following data:
X=np.array(([0,0,1],[0,1,1],[1,0,1],[1,1,1]), dtype=float)
y=np.array(([0,1],[1,0],[1,0],[0,1]), dtype=float)
5. What are the dimension of weight matrix 1 and weight matrix 2? (5pts)
6. Test the two following samples and write down the predicted y values for them. (5 pts)
Testing sample one: X1 = [0, 0, 0] y1=[? ?]
Testing sample two: X2 = [1,1,1] y2=[? ?]
Submission:
Write a report to describe /answer required questions (5 and 6).
Upload your code with comments as a separate .py or zip file.
File1: Assignment5_FirstnameLastname.doc/.pdf (this is the report)
+
File2: Assignment5_ FirstnameLastname.py (this is the code. only “.py” files accepted.
OR
Assignment5_ FirstnameLastname.zip if you have multiple “.py” files.
