IBM and MIT join forces to develop computer vision lab
IBM Research and MIT's Department of Brain and Cognitive Sciences have set up a joint laboratory to advance the field of computer vision.
The IBM-MIT Laboratory for Brain-inspired Multimedia Machine Comprehension (BM3C) will develop cognitive computing systems that emulate the human ability to understand and integrate inputs from multiple sources of audio and visual information. The information will make up a detailed computer representation of the world that can be used in a variety of computer applications in multiple industries.
The collaboration will address the technical challenges around both pattern recognition and prediction methods that are currently impossible for machines alone to accomplish.
For instance, humans watching a short video of a real-world event can easily recognise and produce a verbal description of what happened in the clip as well as assess and predict the likelihood of a variety of subsequent events, but for a machine, this ability is currently impossible.
This could lead to advances that help organisations maintain and repair complex machinery, in addition to helping clinicians improve elderly and disabled care.
‘In a world where humans and machines are working together in increasingly collaborative relationships, breakthroughs in the field of machine vision will potentially help us live healthier, more productive lives,’ said Guru Banavar, chief scientist of cognitive computing and VP at IBM Research. ‘By bringing together brain researchers and computer scientists to solve this complex technical challenge, we will advance the state-of-the-art in AI with our collaborators at MIT.’
IBM will provide technology expertise and advances from its IBM Watson platform to support the Brain and Cognitive Sciences department and the Computer Science and Artificial Intelligence Lab at MIT.
‘Our brain and cognitive scientists are excited to team up with cognitive computing scientists and engineers from IBM to achieve next-generation cognitive computing advances as exposed by next-generation models of the mind,’ said Professor James DiCarlo, leader of the BM3C and head of the Department of Brain and Cognitive Sciences at MIT. ‘We believe that our fields are poised to make key advances in the very challenging domain of unassisted real-world audio-visual understanding and we are looking forward to this new collaboration.’