Assignment #5 - RNNs in Depth
Due Date: 1398/4/19 23:59
Download [problems] [show preview]
Late Policy
- You have free 8 late days.
- You can use late days for assignments. A late day extends the deadline 24 hours.
- Once you have used all 8 late days, the penalty is 10% for each additional late day.
In the final assignment, we’ll build a deep memory-efficient recurrent neural network (RNN) which has residual LSTM cells and a Max-pooling layer. Also, we will try new Byte Pair Encoding (BPE) to improve its performance, and Finally, we will analyze an RNN-based stock predictor to find if it can be utilized in a real-world use case.
Notes
- Students who audit this course should submit their assignments to be qualified for attending the rest of the sessions.
- Finding any sort of copying will zero down that assignment grade and also will be counted as two negative assignment points for your final score.
Setup
- Click on Download [problems] to obtain the assignment jupyter notebook.
- Go to https://colab.research.google.com/.
- Switch to Upload tab, choose
assignment_05.ipynband click upload. - Now You’re ready to go.
Submission
Follow notebook instructions to submit your assignment!