|9 Jun 2020||15:00 - 16:00||Online event|
(Critical) Machine Vision for the Humanities
Leonardo Impett, Cambridge Digital Humanities
Application forms should be returned to CDH Learning (firstname.lastname@example.org) by Friday 22 May 2020. Successful applicants will be notified by 26 May 2020.
This course will introduce graduate students, early-career researchers, and professionals in the humanities to the technologies of image recognition and machine vision, including recent developments in machine vision research in the past half-decade. The course will seek to combine a technical understanding of how machine vision systems work, with a detailed understanding of the possibilities they open to research and study in the humanities, and with a critical exploration of the social, political and ideological dimensions of machine vision.
By the end of the course, students should be able to:
Understand the basic tasks of machine vision, such as Image Classification, Object Detection, Image-to-Image Translation, Image Captioning, Image Segmentation etc.
Understand the fundamental technical operations of image processing and machine vision: the pixel encoding of images, Gaussian and convolutional filters,
Explore critical aspects of machine vision in a technically-informed way: e.g. the problems in algorithmic bias brought about by featureless convolutional networks
Develop and run their own simple machine vision and image processing pipelines, in a visual programming language compiling to Python
Understand the potential synergies and limitations of machine vision applications in humanities research and cultural heritage institutions
The course will be delivered online, with live teaching sessions taking place on Zoom. We will be using Google Drive for collaboration and access to course materials. This course is project-based, and students are highly encouraged to bring with them both their own image datasets (ideally of a hundred or more images) and a set of visual research questions. Students are encouraged to work in teams of 2 or 3, and will be matched by the course leader; but may also apply as a group if they intend to work together.
As the course will use primarily cloud-based computing (even for high-performance computing applications), no specialist computing hardware or specific operating system or software is necessary: just a decent internet connection and modern web browser (even a tablet with keyboard and mobile internet will suffice).
Visual programming languages (i.e. a web app) will be used to teach and prototype machine vision and image processing pipelines: so no previous programming experience is required.
Time commitment and session dates
Sessions on 9, 11 and 25 June will consist of 30 mins presentations and 15 minutes discussion
Project development sessions will consist of an interactive seminar-style session of 60 mins
Office hours consist of a live Q and A session driven by participants’ questions – participation is not compulsory but attendance is encouraged
Participants will be asked to give a 5 min presentation in the final session about their project and will receive feedback and comments from course leaders and invited guest, Alan Blackwell and other participants.
Tues 9 June, 3pm BST: Machine Vision and Humanities Research (45 mins) – ALL
Thurs 11 June, 3pm BST: Technical Fundamentals of Machine Vision (45 mins) – ALL
Tues 16 June, 3pm BST: Project development with students (60 mins) – PROJECTS
Thurs 18 June, 3pm BST: Office hour / drop-in – PROJECTS
Tues 23 June, 3pm BST: Project update with students (60 mins) – PROJECTS
Thurs 25 June, 3pm BST: Critical perspectives on Machine Vision (45 mins) – ALL
Tues 30 June, 3pm BST: Project update with students (60 mins) – PROJECTS
Thurs 2 July, 3pm BST: Office hour / drop in (60 mins) – PROJECTS
Thurs 9th July, 3pm BST: Office hour / drop in (60 mins) – PROJECTS
Tues 14 July, 3pm BST: Participant project presentations and discussion (120 mins) – ALL
This programme is open to graduate students and staff at the University of Cambridge and participants selected for the Cambridge Cultural Heritage Data School.