Compiling Probabilistic, Bio-Inspired Circuits on a Field Programmable Analog Array
A field programmable analog array (FPAA) is presented as an energy efficiency engine: a mixed mode processor for which functions can be compiled at significantly less energy costs using noisy computing circuits. More specifically, it will be shown that the core computation of any dynamical system c...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2014-05-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnins.2014.00086/full |
| _version_ | 1818352643434610688 |
|---|---|
| author | H. Bo eMarr Jennifer eHasler |
| author_facet | H. Bo eMarr Jennifer eHasler |
| author_sort | H. Bo eMarr |
| collection | DOAJ |
| description | A field programmable analog array (FPAA) is presented as an energy efficiency engine: a mixed mode processor for which functions can be compiled at significantly less energy costs using noisy computing circuits. More specifically, it will be shown that the core computation of any dynamical system can be computed on the FPAA at significantly less energy per operation than a digital implementation. A dynamically controllable stochastic system is implemented, which computes Bernoulli random variables, exponentially distributed random variables, and allows for random variables of an arbitrary distribution to be computed. The utility of this system is demonstrated by implementing the well-known Gillespie algorithm for calculating the trajectory of an arbitrary biological system where over a $127X$ performance improvement over current software approaches is shown. The relevance of this approach is extended to any dynamical system. The initial circuits and ideas for this work were generated at the 2008 Telluride Neuromorphic Workshop. |
| first_indexed | 2024-12-13T18:56:54Z |
| format | Article |
| id | doaj.art-b93949653a4649edb24e1d33f293f987 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-13T18:56:54Z |
| publishDate | 2014-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-b93949653a4649edb24e1d33f293f9872022-12-21T23:34:47ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2014-05-01810.3389/fnins.2014.0008670872Compiling Probabilistic, Bio-Inspired Circuits on a Field Programmable Analog ArrayH. Bo eMarr0Jennifer eHasler1RaytheonGeorgia Institute of TechnologyA field programmable analog array (FPAA) is presented as an energy efficiency engine: a mixed mode processor for which functions can be compiled at significantly less energy costs using noisy computing circuits. More specifically, it will be shown that the core computation of any dynamical system can be computed on the FPAA at significantly less energy per operation than a digital implementation. A dynamically controllable stochastic system is implemented, which computes Bernoulli random variables, exponentially distributed random variables, and allows for random variables of an arbitrary distribution to be computed. The utility of this system is demonstrated by implementing the well-known Gillespie algorithm for calculating the trajectory of an arbitrary biological system where over a $127X$ performance improvement over current software approaches is shown. The relevance of this approach is extended to any dynamical system. The initial circuits and ideas for this work were generated at the 2008 Telluride Neuromorphic Workshop.http://journal.frontiersin.org/Journal/10.3389/fnins.2014.00086/fullbio-inspiredFPAAprobability theoryReconfigurable AnalogHardware Acceleratorbiological computational model |
| spellingShingle | H. Bo eMarr Jennifer eHasler Compiling Probabilistic, Bio-Inspired Circuits on a Field Programmable Analog Array Frontiers in Neuroscience bio-inspired FPAA probability theory Reconfigurable Analog Hardware Accelerator biological computational model |
| title | Compiling Probabilistic, Bio-Inspired Circuits on a Field Programmable Analog Array |
| title_full | Compiling Probabilistic, Bio-Inspired Circuits on a Field Programmable Analog Array |
| title_fullStr | Compiling Probabilistic, Bio-Inspired Circuits on a Field Programmable Analog Array |
| title_full_unstemmed | Compiling Probabilistic, Bio-Inspired Circuits on a Field Programmable Analog Array |
| title_short | Compiling Probabilistic, Bio-Inspired Circuits on a Field Programmable Analog Array |
| title_sort | compiling probabilistic bio inspired circuits on a field programmable analog array |
| topic | bio-inspired FPAA probability theory Reconfigurable Analog Hardware Accelerator biological computational model |
| url | http://journal.frontiersin.org/Journal/10.3389/fnins.2014.00086/full |
| work_keys_str_mv | AT hboemarr compilingprobabilisticbioinspiredcircuitsonafieldprogrammableanalogarray AT jenniferehasler compilingprobabilisticbioinspiredcircuitsonafieldprogrammableanalogarray |