IDAS Launch Event

Session

Afternoon 2: Language

Sep 30, 2019, 4:30 PM

OCW 017 (Ogden Centre West)

2. Data Mining and Classical Manuscripts

Peter Heslin (IDAS and Classics)

9/30/19, 4:30 PM

3. Rescribe: OCR for historic texts and manuscripts

Nick White (Rescribe (Durham spin-out))

9/30/19, 4:40 PM

4. Interactive text mining and visualization in the humanities

Donald Sturgeon (Computer Science)

9/30/19, 4:50 PM

5. Digital Theology

Pete Phillips (Theology)

9/30/19, 5:00 PM

6. Machine Learning and Patterns in Dialogue

Chris Brown (Education)

9/30/19, 5:10 PM

7. Deep Learning for Museum Collections

Matthew Roberts (Archaeology)

9/30/19, 5:20 PM

Working with image data provided by the Durham University Oriental Museum, we sought to test how well a data set created from a museum's digital archives could be used for broad artefact type classification using a CNN implemented in PyTorch, as well as considering potential ways in which computer vision and object recognition could be used to support efforts in heritage protection.

8. Statistical Methods in Archaeology

Andrew Millard (Archaeology)

9/30/19, 5:30 PM

34. AI and Ethical Investing

Robert Song

9/30/19, 5:40 PM

35. Mapping Risks in Generated Text

Joe Bullock

9/30/19, 5:50 PM

This talk is based on research conducted in collaboration with the United Nations and demonstrates the ability with which AI can be used to generate text easily, and at a low cost. The implications of this to societal peace and stability will be explored, and recommendations for potential steps towards the mitigation of negative consequences given.