CS 6304 Deep Learning [50 points]
Purpose: The purpose of this assignment is to test concepts on building and training LSTM models.
What to submit: Submit Jupiter notebook that contains code and proper comments. You do not need to submit the data sets.
Refer to the Time Series Classification.ipynb jupyter notebook under week 4. This notebook illustrates how to build and train 1D CNN models to recognize 6 different kinds of human activity based on time series data of 9 features. In this assignment, you will use the same data sets used in the same notebook.
Your goal is to build four models that match the same architecture as the following models in TextClassification_LSTM.ipynb but on the human activity recognition data set. TextClassification_LSTM.ipynb jupyter notebook is under week 5 which illustrates text classification using different LSTM Models.
- layer1_lstm_model
- layer2_lstm_model
- cnn_lstm_model
- bi_lstm_model
For training parameters such as batch size, optimization algorithm etc, you can use the same provided in the notebook TextClassification_LSTM.ipynb. Use early stopping criterion and save the best model. Report the accuracies on the test set.
DescriptionIn this final assignment, the students will demonstrate their ability to apply two ma
Path finding involves finding a path from A to B. Typically we want the path to have certain properties,such as being the shortest or to avoid going t
Develop a program to emulate a purchase transaction at a retail store. Thisprogram will have two classes, a LineItem class and a Transaction class. Th
1 Project 1 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of
1 Project 2 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of