Name
Abstract | ||
|---|---|---|
Compressing real-time input through bandwidth constrained connections has been studied within robotics, wireless sensor networks, and image processing. When there are bandwidth constraints on real- time input the amount of information to be transferred will always be greater than the amount that can be transferred per unit of time. We propose a system that utilizes a local diusion process and a reinforce- ment learning-based memory system to establish a real-time prediction of an entire input space based upon partial observation. The proposed system is optimized for dealing with multi-dimension input spaces, and maintains the ability to react to rare events. Results show the relation of loss to quality and suggest that at higher resolutions gains in quality are possible. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1007/978-3-540-77296-5_16 | 50 Years of Artificial Intelligence |
Keywords | Field | DocType |
bandwidth constraint,higher resolutions gain,real-time prediction,local diffusion process,image processing,entire input space,multi-dimension input space,real-time input,proposed system,reinforcement learning-based memory system,adaptive multi-modal sensor,real time,wireless sensor network | Diffusion process,Computer science,Image processing,Real-time computing,Bandwidth (signal processing),Artificial intelligence,Wireless sensor network,Modal,Robotics,Rare events,Reinforcement learning | Conference |
Volume | ISSN | ISBN |
4850 | 0302-9743 | 3-540-77295-2 |
Citations | PageRank | References |
0 | 0.34 | 13 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kyle Ira Harrington | 1 | 21 | 7.01 |
| Hava T. Siegelmann | 2 | 980 | 145.09 |