Abstract
The design of an auto-associative memory based on a spiking neural network is described. Delays rather than binary values are used to represent signals and coincidence is used to perform pattern matching. A complete implementation of the memory on a single FPGA is presented.
Original language | English |
---|---|
Pages (from-to) | 148-149 |
Number of pages | 2 |
Journal | Electronics Letters |
Volume | 48 |
Issue number | 3 |
DOIs | |
Publication status | Published - 2012 |
Keywords
- associative storage
- field programmable gate arrays
- neural networks (neurobiology)
- pattern matching
- spiking neural networks