An Infinitely Scalable Learning and Recognition Network
Abstract
Common to all these artificial recognition processes are computational and storage requirements that grow with the magnitude of the task. Typically these storage and computational requirements grow linearly or worse with the size of the dataset, a critical problem in a world where data storage demand is outstripping capability (see Figure 1), and this gap is forecast to continue growing (1). There is currently no feasible solution to this problem – current techniques such as those used for video and image compression have plateaued in performance over the last decade, while the limits of hash based approaches are known and unlikely to provide an ultimate solution. This project combines modelling of and inspiration from the spatial memory encoding system in the mammalian brain with machine learning techniques to enable sub linear storage growth; that is, as the number of “items” in the database (places, images, voice signatures etc.) that need to be encoded grows, the amount of storage space required per item continually decreases.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jan 14, 2022
- Source ID
- FA23861914079
Entities
People
- Michael Milford
Organizations
- Air Force Office of Scientific Research
- Queensland University of Technology
- United States Air Force