4/28/22, 7:08 PM Machine Learning as a Service Machine Learning as a Service 0/12 Points 11/16/2021 Attempt 1
REVIEW FEEDBACK Offline Score: View Feedback 0/12 Unlimited Attempts Allowed Details Module A Create an iOS application using the HTTPSwiftExample that: Collects some form of low throughput (sampling rate > 1s) feature data for processing: audio, video, motion, or from the micro-controller Uploads labeled feature data to a server via HTTP POST requests you can run the server from your laptop or mac mini Alternatively you can use a virtual machine, AWS, or other cloud service Trains a model from the labeled data (e.g., KNN, SVM, Random Forest, etc.) Requests predictions from the server by uploading unknown feature vectors can be periodically or initiated by user Note that the server code given to you will automatically save any feature data you upload and train a machine learning model, given the correct POST/GET request commands You should not need to update the server for any of the given functionality. However, the predictions from the server may not be sufficient without updating the training parameters or the type of model used. The type of prediction used in this lab should be sufficiently different than the in-class example. You have a lot of free reign in this assignment to create something interesting and unique. Try to make this one iteration of the final project. Module B: Update the HTTPExample and the tornado web server to: Specify the type of model to use in the Machine Learning via the iOS POST request(s) at least two different types of machine learning models (e.g., SVM and KNN) Compare the efficacy of two or more different models send parameters to use in the machine learning models from the phone (e.g., number of neighbors to use in KNN) Exceptional Work: 7000 Level Students Choose ONE of the following: Implement authentication in tornado and in your iOS application https://smu.instructure.com/courses/88454/assignments/573114 1/4 4/28/22, 7:08 PM Machine Learning as a Service Use CoreML to export your custom trained machine learning model and run the machine learning prediction locally on the iOS app (NOTE: the CoreML model must be exported from the data you create on your HTTPServer) Also, the CoreML implementation should sufficiently different from the class example. Turn In: 1. The source code for your app in zipped format or GitHub Link. Use proper coding techniques and naming conventions for objective C and swift. 2. Your team member names and team name in the comments of the "main.m" files as well as in upload text. 3. A video of your app working as intended 4. The final project proposal is due at the same time as this assignment. View Rubric https://smu.instructure.com/courses/88454/assignments/573114 2/4 4/28/22, 7:08 PM Machine Learning as a Service Lab Five: ML Criteria Ratings Pts Proper UI Design view longer description / 2 pts Feature Design view longer description / 2 pts Module A: Feature Data view longer description / 2 pts Module A: Data to Server with Predictions view longer description / 2 pts Module A: Errors Handled Properly / 1 pts Module B: Different Models view longer description Exceptional Credit view longer description Total Points: 0 / 2 pts / 1 pts Choose a file to upload https://smu.instructure.com/courses/88454/assignments/573114 3/4 4/28/22, 7:08 PM Machine Learning as a Service You are unable to submit to this assignment as your enrollment in this course has been concluded. https://smu.instructure.com/courses/88454/assignments/573114 4/4