US AFOSR / AOARD: An infinitely scalable learning and recognition network
Project dates: 09/01/2016 - 09/01/2020
Learning and recognition are a fundamental process performed by animals, humans, robots and intelligent systems. Humans, for example, continually learn and recognize where they are in the world (place recognition), who is there with them (facial recognition) and what things are around them (object recognition). Recognition also plays a significant role in technology like smartphones, whether it be recognizing what you are saying (voice recognition) or what the consumer item in front of you is when using Google Goggles (object recognition). Google and other information aggregators perform recognition at a vast scale, recognizing and classifying billions of images in the cloud and house numbers in millions of kilometres of Google Streetview imagery. In security and surveillance, task-specific signatures (such as a specific person’s voice, a bomb-carrying back pack or a person’s face) must be automatically recognized amongst vast amounts of data. Because data storage and collection is expensive, it is necessary to build new techniques to store and process data.
This project combines modelling of the spatial memory encoding system in the mammalian brain with machine learning techniques to achieve new levels of data storage compression for learning and recall systems.
- Sourav Garg, Michael Milford, “Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations“, in IEEE International Conference on Robotics and Automation, 2020.
- Huu Le, Ming Xu, Tuan Hoang, and Michael Milford, “Hierarchical Encoding of Sequential Data with Compact and Sub-linear Storage Cost”, International Conference on Computer Vision, Seoul, Korea, 2019.
- Huu Le, Tuan Hoang, Michael J Milford, “BTEL: A Binary Tree Encoding Approach for Visual Localization”, in press in IEEE Robotics and Automation Letters, 2019.
- Huu Le, Thanh-Toan Do, Anders Eriksson, Michael Milford, “A Binary Optimization Approach for Constrained K-Means Clustering”, Asian Conference on Computer Vision, Perth, Australia, 2018.
- Litao Yu, Adam Jacobson and Michael Milford, “Rhythmic Representations: Learning Periodic Patterns for Scalable Place Recognition at a Sublinear Storage Cost”, in IEEE Robotics and Automation Letters, 3(2), April 2018.
- Adam Jacobson, Walter Scheirer, Michael J Milford, “Deja vu: Scalable Place Recognition Using Mutually Supportive Feature Frequencies”, in IEEE International Conference on Intelligent Robots, 2017.
Other Team Members
- Litao Yu
- Adam Jacobson
- Huu Le
AOARD / AFOSR
- LtCol Alan Lin
- Dr Peter Friedland
- US Air Force Office of Scientific Research (AFOSR) / Asian Office of Aerospace Research and Development (AOARD)
We combine neuroscience and robotic algorithms to create new technologies for compressing and storing data such as navigational maps.