equanimous
Norse clairvoyant shapeshifter goddess
he following article makes clear that NASA and DARPA have been anxiously awaiting a chip like AKIDA from at least 2013. At that time they were anticipating an analogue solution not knowing Peter and Anil were on a digital SNN fast track:
“Spiking Neurons for Analysis of Patterns
High-performance pattern-analysis systems could be implemented as analog VLSI circuits. NASA’s Jet Propulsion Laboratory, Pasadena, California
Artificial neural networks comprising spiking neurons of a novel type have been conceived as improved pattern- analysis and pattern-recognition compu- tational systems. These neurons are rep- resented by a mathematical model denoted the state-variable model (SVM), which among other things, exploits a computational parallelism inherent in spiking-neuron geometry. Networks of SVM neurons offer advantages of speed and computational efficiency, relative to traditional artificial neural networks. The SVM also overcomes some of the limita- tions of prior spiking-neuron models. There are numerous potential pattern- recognition, tracking, and data-reduction (data preprocessing) applications for these SVM neural networks on Earth and in exploration of remote planets.
Spiking neurons imitate biological neu- rons more closely than do the neurons of traditional artificial neural networks. A spiking neuron includes a central cell body (soma) surrounded by a treelike intercon- nection network (dendrites). Spiking neu- rons are so named because they generate trains of output pulses (spikes) in response to inputs received from sensors or from other neurons. They gain their speed ad- vantage over traditional neural networks by using the timing of individual spikes for
computation, whereas traditional artificial neurons use averages of activity levels over time. Moreover, spiking neurons use the delays inherent in dendritic processing in order to efficiently encode the information content of incoming signals. Because tradi- tional artificial neurons fail to capture this encoding, they have less processing capa- bility, and so it is necessary to use more gates when implementing traditional artifi- cial neurons in electronic circuitry. Such higher-order functions as dynamic tasking are effected by use of pools (collections) of spiking neurons interconnected by spike- transmitting fibers.
The SVM includes adaptive thresholds and submodels of transport of ions (in imitation of such transport in biological neurons). These features enable the neurons to adapt their responses to high-rate inputs from sensors, and to adapt their firing thresholds to mitigate noise or effects of potential sensor fail- ure. The mathematical derivation of the SVM starts from a prior model, known in the art as the point soma model, which captures all of the salient properties of neuronal response while keeping the computational cost low. The point-soma latency time is modified to be an expo- nentially decaying function of the strength of the applied potential.
Choosing computational efficiency over biological fidelity, the dendrites sur- rounding a neuron are represented by simplified compartmental submodels and there are no dendritic spines. Up- dates to the dendritic potential, calcium- ion concentrations and conductances, and potassium-ion conductances are done by use of equations similar to those of the point soma. Diffusion processes in dendrites are modeled by averaging among nearest-neighbor compartments. Inputs to each of the dendritic compart- ments come from sensors. Alternatively or in addition, when an affected neuron is part of a pool, inputs can come from other spiking neurons.
At present, SVM neural networks are im- plemented by computational simulation, using algorithms that encode the SVM and its submodels. However, it should be possi- ble to implement these neural networks in hardware: The differential equations for the dendritic and cellular processes in the SVM model of spiking neurons map to equivalent circuits that can be imple- mented directly in analog very-large-scale integrated (VLSI) circuits.
This work was done by Terrance Hunts- berger of Caltech for NASA’s Jet Propulsion Laboratory.”
ntrs.nasa.gov
“Spiking Neurons for Analysis of Patterns
High-performance pattern-analysis systems could be implemented as analog VLSI circuits. NASA’s Jet Propulsion Laboratory, Pasadena, California
Artificial neural networks comprising spiking neurons of a novel type have been conceived as improved pattern- analysis and pattern-recognition compu- tational systems. These neurons are rep- resented by a mathematical model denoted the state-variable model (SVM), which among other things, exploits a computational parallelism inherent in spiking-neuron geometry. Networks of SVM neurons offer advantages of speed and computational efficiency, relative to traditional artificial neural networks. The SVM also overcomes some of the limita- tions of prior spiking-neuron models. There are numerous potential pattern- recognition, tracking, and data-reduction (data preprocessing) applications for these SVM neural networks on Earth and in exploration of remote planets.
Spiking neurons imitate biological neu- rons more closely than do the neurons of traditional artificial neural networks. A spiking neuron includes a central cell body (soma) surrounded by a treelike intercon- nection network (dendrites). Spiking neu- rons are so named because they generate trains of output pulses (spikes) in response to inputs received from sensors or from other neurons. They gain their speed ad- vantage over traditional neural networks by using the timing of individual spikes for
computation, whereas traditional artificial neurons use averages of activity levels over time. Moreover, spiking neurons use the delays inherent in dendritic processing in order to efficiently encode the information content of incoming signals. Because tradi- tional artificial neurons fail to capture this encoding, they have less processing capa- bility, and so it is necessary to use more gates when implementing traditional artifi- cial neurons in electronic circuitry. Such higher-order functions as dynamic tasking are effected by use of pools (collections) of spiking neurons interconnected by spike- transmitting fibers.
The SVM includes adaptive thresholds and submodels of transport of ions (in imitation of such transport in biological neurons). These features enable the neurons to adapt their responses to high-rate inputs from sensors, and to adapt their firing thresholds to mitigate noise or effects of potential sensor fail- ure. The mathematical derivation of the SVM starts from a prior model, known in the art as the point soma model, which captures all of the salient properties of neuronal response while keeping the computational cost low. The point-soma latency time is modified to be an expo- nentially decaying function of the strength of the applied potential.
Choosing computational efficiency over biological fidelity, the dendrites sur- rounding a neuron are represented by simplified compartmental submodels and there are no dendritic spines. Up- dates to the dendritic potential, calcium- ion concentrations and conductances, and potassium-ion conductances are done by use of equations similar to those of the point soma. Diffusion processes in dendrites are modeled by averaging among nearest-neighbor compartments. Inputs to each of the dendritic compart- ments come from sensors. Alternatively or in addition, when an affected neuron is part of a pool, inputs can come from other spiking neurons.
At present, SVM neural networks are im- plemented by computational simulation, using algorithms that encode the SVM and its submodels. However, it should be possi- ble to implement these neural networks in hardware: The differential equations for the dendritic and cellular processes in the SVM model of spiking neurons map to equivalent circuits that can be imple- mented directly in analog very-large-scale integrated (VLSI) circuits.
This work was done by Terrance Hunts- berger of Caltech for NASA’s Jet Propulsion Laboratory.”
Spiking Neurons for Analysis of Patterns - NASA Technical Reports Server (NTRS)
Artificial neural networks comprising spiking neurons of a novel type have been conceived as improved pattern-analysis and pattern-recognition computational systems. These neurons are represented by a mathematical model denoted the state-variable model (SVM), which among other things, exploits a...
Last edited:
