Interactive Media Arts (IMA) at NYU Shanghai
- Course Note Fall 2020
- W09 What is Neural Network?, KNN Classification, Assignment
- W08 Midterm Project Presentations & Peer Review
- W07 Midterm Project Proposals, Peer Review & Studio Time
- W06 PitchDection(CREPE), Assignment
- W05 BodyPix [Introduction, ml5.js], UNET [Introduction, ml5.js], Assignment
- W04 PoseNet [Introduction, Tensorflow/Github, ml5.js], Assignment
- W03 Slides, Assignment
- W02 Slides, Case Study
- W01 Slides, Assignment
- Syllabus
- Resources
- Instructor: J.H. Moon
- Office: Room 939
- Office Hours: Thursdays, 2pm – 5pm. Room 939 or Zoom. (By appointment)
- Virtual Office Hours: Anytime (via Slack direct message or email)
- Class meeting days and times: 3:15pm to 6:15pm, Tuesday
- Class room number: Room 824 or Zoom
- Course Schedule Overview
- Course Policies
Machine Learning for New Interfaces is an introductory course with the goal of teaching machine learning concepts in an approachable way to students with no prior knowledge.
We will explore diverse and experimental methods in Machine Learning such as classification, recognition, movement prediction and image style translation. By the end of the course, students will be able to create their own interfaces or applications for the web. They will be able to apply fundamental concepts of Machine Learning, recognize Machine Learning models in the world and make Machine Learning projects applicable to everyday life.
Learning and teaching Machine Learning can be a daunting task. This class seeks to reverse the conventional methods of teaching Machine Learning by applying a more friendly and approachable style, masking the complexity of the concepts and technologies.
Students will learn the fundamentals of programming first. Then they will use existing machine learning models (pre-trained) and apply them to their own ideas and outputs, similar to the way we utilize physical sensors in Interaction Lab or devices such as Leap Motion and Kinect without a full understanding of its construction or blueprint. Directly experiencing these diverse pre-trained models and techniques, they will apply, step by step, the fundamentals and core concepts of Machine Learning.
Throughout the course, students will gain the skills to develop meaningful and effective user interactions. By utilizing diverse methods of motion tracking by the models, they will create innovative and interactive interfaces on the web or mobile platform. Both practical and creative applications are to be investigated as students are challenged to design their own solutions.
Upon completion of this course, students will be able to:
- broaden their knowledge and experience in Machine Learning;
- practice and produce the fundamentals of programming;
- demonstrate Object-oriented Programming and integrate why/how to use the concept into practical applications;
- apply diverse machine learning techniques to their own ideas and practices;
- visualize and simulate various data from Machine Learning Models;
- create innovative, practical and interactive interfaces on the web or mobile platform with machine learning models;
- produce generative art and/or creative applications by utilizing a combination of concepts and techniques discussed over the course, and;
- discuss and develop meaningful and effective user interactions.