back to Introduction to Neural Networks (CSE 40868/60868)

Assignments

Assignment 3: Recurrent Neural Networks in TensorFlow / Keras.
You will build the RNN and apply it to process time series data.

Things to do:

1. Use this github repo prepared by Toan Nguyen to access the tutorial and assignment.
2. Upload your solution (code + short report) into the 'assignment3' subfolder created in your dropbox (/afs/nd.edu/coursefa.16/cse/cse{40868.01,60868.01}/dropbox) no later than by Wednesday, Dec. 7, 11:59pm.
3. If you have questions, ask Toan (tnguye28@nd.edu)

Grading:

1. 20 points for a correct solution just following the assignment.
2. 2 extra points for your additional effort.

Assignment 2: Convolutional Neural Networks in TensorFlow.
You will build the CNN and apply it to visual object recognition.

Things to do:

1. Use this github repo prepared by Toan Nguyen to access the tutorial and assignment.
2. Upload your solution (code + short report) into the 'assignment2' subfolder created in your dropbox (/afs/nd.edu/coursefa.16/cse/cse{40868.01,60868.01}/dropbox) no later than by Monday, Nov. 21, 11:59pm.
3. If you have questions, ask Toan (tnguye28@nd.edu)

Grading:

1. 25 points for a correct solution just following the assignment.
2. 2 extra points for your additional effort (for instance visualization of learned kernels).

Assignment 1: Multilayer perceptrons in Keras.
You will build multilayer perceptrons in Keras and check their properties.

Things to do:

1. Use this github repo prepared by Toan Nguyen to access the assignment.
2. Upload your solution (code + short report) into the 'assignment1' subfolder created in your dropbox (/afs/nd.edu/coursefa.16/cse/cse{40868.01,60868.01}/dropbox) no later than by Wednesday, Oct. 26, 11:59pm.
3. If you have questions, ask Toan (tnguye28@nd.edu)

Grading:

1. 10 points for a correct solution just following the assignment.
2. 1 extra point for your additional effort (use of additional dataset, testing NN parameters not mentioned in the assignment, etc.).