A neuromorphic architecture for object recognition and motion anticipation using burst-STDP.
In this work we investigate the possibilities offered by a minimal framework of artificial spiking neurons to be deployed in silico. Here we introduce a hierarchical network architecture of spiking neurons which learns to recognize moving objects in a visual environment and determine the correct mot...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2012-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC3352850?pdf=render |
| _version_ | 1818027105671184384 |
|---|---|
| author | Andrew Nere Umberto Olcese David Balduzzi Giulio Tononi |
| author_facet | Andrew Nere Umberto Olcese David Balduzzi Giulio Tononi |
| author_sort | Andrew Nere |
| collection | DOAJ |
| description | In this work we investigate the possibilities offered by a minimal framework of artificial spiking neurons to be deployed in silico. Here we introduce a hierarchical network architecture of spiking neurons which learns to recognize moving objects in a visual environment and determine the correct motor output for each object. These tasks are learned through both supervised and unsupervised spike timing dependent plasticity (STDP). STDP is responsible for the strengthening (or weakening) of synapses in relation to pre- and post-synaptic spike times and has been described as a Hebbian paradigm taking place both in vitro and in vivo. We utilize a variation of STDP learning, called burst-STDP, which is based on the notion that, since spikes are expensive in terms of energy consumption, then strong bursting activity carries more information than single (sparse) spikes. Furthermore, this learning algorithm takes advantage of homeostatic renormalization, which has been hypothesized to promote memory consolidation during NREM sleep. Using this learning rule, we design a spiking neural network architecture capable of object recognition, motion detection, attention towards important objects, and motor control outputs. We demonstrate the abilities of our design in a simple environment with distractor objects, multiple objects moving concurrently, and in the presence of noise. Most importantly, we show how this neural network is capable of performing these tasks using a simple leaky-integrate-and-fire (LIF) neuron model with binary synapses, making it fully compatible with state-of-the-art digital neuromorphic hardware designs. As such, the building blocks and learning rules presented in this paper appear promising for scalable fully neuromorphic systems to be implemented in hardware chips. |
| first_indexed | 2024-12-10T04:42:37Z |
| format | Article |
| id | doaj.art-072034cc651d42a088c751d290ae063e |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-10T04:42:37Z |
| publishDate | 2012-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-072034cc651d42a088c751d290ae063e2022-12-22T02:01:51ZengPublic Library of Science (PLoS)PLoS ONE1932-62032012-01-0175e3695810.1371/journal.pone.0036958A neuromorphic architecture for object recognition and motion anticipation using burst-STDP.Andrew NereUmberto OlceseDavid BalduzziGiulio TononiIn this work we investigate the possibilities offered by a minimal framework of artificial spiking neurons to be deployed in silico. Here we introduce a hierarchical network architecture of spiking neurons which learns to recognize moving objects in a visual environment and determine the correct motor output for each object. These tasks are learned through both supervised and unsupervised spike timing dependent plasticity (STDP). STDP is responsible for the strengthening (or weakening) of synapses in relation to pre- and post-synaptic spike times and has been described as a Hebbian paradigm taking place both in vitro and in vivo. We utilize a variation of STDP learning, called burst-STDP, which is based on the notion that, since spikes are expensive in terms of energy consumption, then strong bursting activity carries more information than single (sparse) spikes. Furthermore, this learning algorithm takes advantage of homeostatic renormalization, which has been hypothesized to promote memory consolidation during NREM sleep. Using this learning rule, we design a spiking neural network architecture capable of object recognition, motion detection, attention towards important objects, and motor control outputs. We demonstrate the abilities of our design in a simple environment with distractor objects, multiple objects moving concurrently, and in the presence of noise. Most importantly, we show how this neural network is capable of performing these tasks using a simple leaky-integrate-and-fire (LIF) neuron model with binary synapses, making it fully compatible with state-of-the-art digital neuromorphic hardware designs. As such, the building blocks and learning rules presented in this paper appear promising for scalable fully neuromorphic systems to be implemented in hardware chips.http://europepmc.org/articles/PMC3352850?pdf=render |
| spellingShingle | Andrew Nere Umberto Olcese David Balduzzi Giulio Tononi A neuromorphic architecture for object recognition and motion anticipation using burst-STDP. PLoS ONE |
| title | A neuromorphic architecture for object recognition and motion anticipation using burst-STDP. |
| title_full | A neuromorphic architecture for object recognition and motion anticipation using burst-STDP. |
| title_fullStr | A neuromorphic architecture for object recognition and motion anticipation using burst-STDP. |
| title_full_unstemmed | A neuromorphic architecture for object recognition and motion anticipation using burst-STDP. |
| title_short | A neuromorphic architecture for object recognition and motion anticipation using burst-STDP. |
| title_sort | neuromorphic architecture for object recognition and motion anticipation using burst stdp |
| url | http://europepmc.org/articles/PMC3352850?pdf=render |
| work_keys_str_mv | AT andrewnere aneuromorphicarchitectureforobjectrecognitionandmotionanticipationusingburststdp AT umbertoolcese aneuromorphicarchitectureforobjectrecognitionandmotionanticipationusingburststdp AT davidbalduzzi aneuromorphicarchitectureforobjectrecognitionandmotionanticipationusingburststdp AT giuliotononi aneuromorphicarchitectureforobjectrecognitionandmotionanticipationusingburststdp AT andrewnere neuromorphicarchitectureforobjectrecognitionandmotionanticipationusingburststdp AT umbertoolcese neuromorphicarchitectureforobjectrecognitionandmotionanticipationusingburststdp AT davidbalduzzi neuromorphicarchitectureforobjectrecognitionandmotionanticipationusingburststdp AT giuliotononi neuromorphicarchitectureforobjectrecognitionandmotionanticipationusingburststdp |