Limits...
Implementation of olfactory bulb glomerular-layer computations in a digital neurosynaptic core.

Imam N, Cleland TA, Manohar R, Merolla PA, Arthur JV, Akopyan F, Modha DS - Front Neurosci (2012)

Bottom Line: Our system is based on a digital neuromorphic chip consisting of 256 leaky-integrate-and-fire neurons, 1024 × 256 crossbar synapses, and address-event representation communication circuits.The neural circuits configured in the chip reflect established connections among mitral cells, periglomerular cells, external tufted cells, and superficial short-axon cells within the olfactory bulb, and accept input from convergent sets of sensors configured as olfactory sensory neurons.Our circuits, consuming only 45 pJ of active power per spike with a power supply of 0.85 V, can be used as the first stage of processing in low-power artificial chemical sensing devices inspired by natural olfactory systems.

View Article: PubMed Central - PubMed

Affiliation: Computer Systems Lab, Department of Electrical and Computer Engineering, Cornell University Ithaca, NY, USA.

ABSTRACT
We present a biomimetic system that captures essential functional properties of the glomerular layer of the mammalian olfactory bulb, specifically including its capacity to decorrelate similar odor representations without foreknowledge of the statistical distributions of analyte features. Our system is based on a digital neuromorphic chip consisting of 256 leaky-integrate-and-fire neurons, 1024 × 256 crossbar synapses, and address-event representation communication circuits. The neural circuits configured in the chip reflect established connections among mitral cells, periglomerular cells, external tufted cells, and superficial short-axon cells within the olfactory bulb, and accept input from convergent sets of sensors configured as olfactory sensory neurons. This configuration generates functional transformations comparable to those observed in the glomerular layer of the mammalian olfactory bulb. Our circuits, consuming only 45 pJ of active power per spike with a power supply of 0.85 V, can be used as the first stage of processing in low-power artificial chemical sensing devices inspired by natural olfactory systems.

No MeSH data available.


Related in: MedlinePlus

Top: The architecture of the neurosynaptic core. Each core consists of an array of neurons, a crossbar array of synapses (bounded by gray box) and AER receiver (decoder) and transmitter. Each junction in the crossbar represents a potential synapse between an axon (row) and dendrite (column). An example sequence of events in the core is illustrated. The AER decoder accepts an incoming address event and activates axon 3 (A3) by asserting the third wordline of the SRAM crossbar array. As a result, a synaptic event of type G3 is delivered to neurons N1, N3, and NM. The AER transmitter sends out the addresses of these neurons if they consequently spike. Bottom: Parameters and state variables of the system.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3368244&req=5

Figure 2: Top: The architecture of the neurosynaptic core. Each core consists of an array of neurons, a crossbar array of synapses (bounded by gray box) and AER receiver (decoder) and transmitter. Each junction in the crossbar represents a potential synapse between an axon (row) and dendrite (column). An example sequence of events in the core is illustrated. The AER decoder accepts an incoming address event and activates axon 3 (A3) by asserting the third wordline of the SRAM crossbar array. As a result, a synaptic event of type G3 is delivered to neurons N1, N3, and NM. The AER transmitter sends out the addresses of these neurons if they consequently spike. Bottom: Parameters and state variables of the system.

Mentions: The digital neurosynaptic core in the chip consists of 256 single-compartment leaky-integrate-and-fire neurons, a 1024 × 256 crossbar synapse array, and communication circuits to transfer spike trains (Figure 2). The crossbar array is freely configurable so that arbitrary networks can be set up in the system. Each row of the crossbar corresponds to an axon which is driven by off-chip sensor arrays or by one of the on-chip neurons. Each column corresponds to a dendrite of a particular neuron. A memory cell resides at each intersection of a row and a column, and the state of this cell represents whether or not a connection exists between that particular axon-dendrite pair. Hence, each neuron may receive up to 1024 synaptic inputs (via its dendrite) depending on the configuration of the crossbar and the activity of the axons.


Implementation of olfactory bulb glomerular-layer computations in a digital neurosynaptic core.

Imam N, Cleland TA, Manohar R, Merolla PA, Arthur JV, Akopyan F, Modha DS - Front Neurosci (2012)

Top: The architecture of the neurosynaptic core. Each core consists of an array of neurons, a crossbar array of synapses (bounded by gray box) and AER receiver (decoder) and transmitter. Each junction in the crossbar represents a potential synapse between an axon (row) and dendrite (column). An example sequence of events in the core is illustrated. The AER decoder accepts an incoming address event and activates axon 3 (A3) by asserting the third wordline of the SRAM crossbar array. As a result, a synaptic event of type G3 is delivered to neurons N1, N3, and NM. The AER transmitter sends out the addresses of these neurons if they consequently spike. Bottom: Parameters and state variables of the system.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3368244&req=5

Figure 2: Top: The architecture of the neurosynaptic core. Each core consists of an array of neurons, a crossbar array of synapses (bounded by gray box) and AER receiver (decoder) and transmitter. Each junction in the crossbar represents a potential synapse between an axon (row) and dendrite (column). An example sequence of events in the core is illustrated. The AER decoder accepts an incoming address event and activates axon 3 (A3) by asserting the third wordline of the SRAM crossbar array. As a result, a synaptic event of type G3 is delivered to neurons N1, N3, and NM. The AER transmitter sends out the addresses of these neurons if they consequently spike. Bottom: Parameters and state variables of the system.
Mentions: The digital neurosynaptic core in the chip consists of 256 single-compartment leaky-integrate-and-fire neurons, a 1024 × 256 crossbar synapse array, and communication circuits to transfer spike trains (Figure 2). The crossbar array is freely configurable so that arbitrary networks can be set up in the system. Each row of the crossbar corresponds to an axon which is driven by off-chip sensor arrays or by one of the on-chip neurons. Each column corresponds to a dendrite of a particular neuron. A memory cell resides at each intersection of a row and a column, and the state of this cell represents whether or not a connection exists between that particular axon-dendrite pair. Hence, each neuron may receive up to 1024 synaptic inputs (via its dendrite) depending on the configuration of the crossbar and the activity of the axons.

Bottom Line: Our system is based on a digital neuromorphic chip consisting of 256 leaky-integrate-and-fire neurons, 1024 × 256 crossbar synapses, and address-event representation communication circuits.The neural circuits configured in the chip reflect established connections among mitral cells, periglomerular cells, external tufted cells, and superficial short-axon cells within the olfactory bulb, and accept input from convergent sets of sensors configured as olfactory sensory neurons.Our circuits, consuming only 45 pJ of active power per spike with a power supply of 0.85 V, can be used as the first stage of processing in low-power artificial chemical sensing devices inspired by natural olfactory systems.

View Article: PubMed Central - PubMed

Affiliation: Computer Systems Lab, Department of Electrical and Computer Engineering, Cornell University Ithaca, NY, USA.

ABSTRACT
We present a biomimetic system that captures essential functional properties of the glomerular layer of the mammalian olfactory bulb, specifically including its capacity to decorrelate similar odor representations without foreknowledge of the statistical distributions of analyte features. Our system is based on a digital neuromorphic chip consisting of 256 leaky-integrate-and-fire neurons, 1024 × 256 crossbar synapses, and address-event representation communication circuits. The neural circuits configured in the chip reflect established connections among mitral cells, periglomerular cells, external tufted cells, and superficial short-axon cells within the olfactory bulb, and accept input from convergent sets of sensors configured as olfactory sensory neurons. This configuration generates functional transformations comparable to those observed in the glomerular layer of the mammalian olfactory bulb. Our circuits, consuming only 45 pJ of active power per spike with a power supply of 0.85 V, can be used as the first stage of processing in low-power artificial chemical sensing devices inspired by natural olfactory systems.

No MeSH data available.


Related in: MedlinePlus