The Ripple Pond: Enabling Spiking Networks to See
We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns suitable for recognition by temporal coding learning and memory networks. The RPN has been...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2013-11-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnins.2013.00212/full |
| _version_ | 1818511878047924224 |
|---|---|
| author | Saeed eAfshar Saeed eAfshar Greg Kevin Cohen Runchun Mark Wang André evan Schaik Jonathan eTapson Torsten eLehmann Tara Julia Hamilton Tara Julia Hamilton |
| author_facet | Saeed eAfshar Saeed eAfshar Greg Kevin Cohen Runchun Mark Wang André evan Schaik Jonathan eTapson Torsten eLehmann Tara Julia Hamilton Tara Julia Hamilton |
| author_sort | Saeed eAfshar |
| collection | DOAJ |
| description | We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for information processing, using dimensional collapse of imagery information into amenable temporal patterns and the use of asynchronous frames for information binding. |
| first_indexed | 2024-12-10T23:39:01Z |
| format | Article |
| id | doaj.art-32b0c084bd2c4db6b9f062403cbf1d90 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-10T23:39:01Z |
| publishDate | 2013-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-32b0c084bd2c4db6b9f062403cbf1d902022-12-22T01:29:05ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2013-11-01710.3389/fnins.2013.0021258662The Ripple Pond: Enabling Spiking Networks to SeeSaeed eAfshar0Saeed eAfshar1Greg Kevin Cohen2Runchun Mark Wang3André evan Schaik4Jonathan eTapson5Torsten eLehmann6Tara Julia Hamilton7Tara Julia Hamilton8University of Western SydneyThe University of New South WalesUniversity of Western SydneyUniversity of Western SydneyUniversity of Western SydneyUniversity of Western SydneyThe University of New South WalesUniversity of Western SydneyThe University of New South WalesWe present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for information processing, using dimensional collapse of imagery information into amenable temporal patterns and the use of asynchronous frames for information binding.http://journal.frontiersin.org/Journal/10.3389/fnins.2013.00212/fullneuromorphic engineeringobject recognitiontemporal codingSpiking Neural networkpolychronous networkimage transformation invariance |
| spellingShingle | Saeed eAfshar Saeed eAfshar Greg Kevin Cohen Runchun Mark Wang André evan Schaik Jonathan eTapson Torsten eLehmann Tara Julia Hamilton Tara Julia Hamilton The Ripple Pond: Enabling Spiking Networks to See Frontiers in Neuroscience neuromorphic engineering object recognition temporal coding Spiking Neural network polychronous network image transformation invariance |
| title | The Ripple Pond: Enabling Spiking Networks to See |
| title_full | The Ripple Pond: Enabling Spiking Networks to See |
| title_fullStr | The Ripple Pond: Enabling Spiking Networks to See |
| title_full_unstemmed | The Ripple Pond: Enabling Spiking Networks to See |
| title_short | The Ripple Pond: Enabling Spiking Networks to See |
| title_sort | ripple pond enabling spiking networks to see |
| topic | neuromorphic engineering object recognition temporal coding Spiking Neural network polychronous network image transformation invariance |
| url | http://journal.frontiersin.org/Journal/10.3389/fnins.2013.00212/full |
| work_keys_str_mv | AT saeedeafshar theripplepondenablingspikingnetworkstosee AT saeedeafshar theripplepondenablingspikingnetworkstosee AT gregkevincohen theripplepondenablingspikingnetworkstosee AT runchunmarkwang theripplepondenablingspikingnetworkstosee AT andreevanschaik theripplepondenablingspikingnetworkstosee AT jonathanetapson theripplepondenablingspikingnetworkstosee AT torstenelehmann theripplepondenablingspikingnetworkstosee AT tarajuliahamilton theripplepondenablingspikingnetworkstosee AT tarajuliahamilton theripplepondenablingspikingnetworkstosee AT saeedeafshar ripplepondenablingspikingnetworkstosee AT saeedeafshar ripplepondenablingspikingnetworkstosee AT gregkevincohen ripplepondenablingspikingnetworkstosee AT runchunmarkwang ripplepondenablingspikingnetworkstosee AT andreevanschaik ripplepondenablingspikingnetworkstosee AT jonathanetapson ripplepondenablingspikingnetworkstosee AT torstenelehmann ripplepondenablingspikingnetworkstosee AT tarajuliahamilton ripplepondenablingspikingnetworkstosee AT tarajuliahamilton ripplepondenablingspikingnetworkstosee |