Robert Keeling - Sidley Austin
Jianping Zhang - Ankura Consulting Group, LLP
Nathaniel Huber-Fliflet - Ankura
Image processing, powered by deep learning technology, has made great advances in the last decade and is now effective at providing accurate results for challenging machine learning tasks including image classification, image clustering, and object detection. Deep learning is the same technology that the AlphaGo program used to beat the 18-time world Go champion Lee Sedol, a feat that some machine learning scientists described as a ‘spooky result’. Deep learning is an incredibly powerful technology which can help lawyers more effectively identify and analyze images within their reviews.
Image classification, image clustering, and object detection are helping lawyers mine their data sets for handwriting, personal photos to assist with privacy regulations, the state of a construction site before and after a major event, pornography, and many other applications. These technologies are also helping to exclude irrelevant logos and pictures from review to reduce costs, as well as organizing similar types of pictures together for a
quick assessment of their content.
This session will:
- Describe what deep learning technology is and how it works
- Examine the use cases where deep learning can provide significant benefit to lawyers
- Demonstrate how the technology is applied in a legal document review