Hardware spiking neural network with run-time reconfigurable connectivity in an autonomous robot

Roggen, Daniel; Hofmann, Stefan; Thoma, Yann; Floreano, Dario

doi:10.1109/eh.2003.1217666

Cited by 51 publications

(30 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is especially so for spiking neural networks (SNNs). Examples of SNN implementations that do exhibit on-chip learning are in [5] and [6], where the networks were evolved using a genetic algorithm run on a microprocessor. Spiking neural networks presently account for only a minority of the connectionist system implementations on FPGA.…”

Section: Introductionmentioning

confidence: 99%

FPGA Implementation of an Evolving Spiking Neural Network

Zuppicich

Soltic

2009

Advances in Neuro-Information Processing

View full text Add to dashboard Cite

Abstract. This research presents a Field Programmable Gate Array (FPGA) implementation of a taste recognition model. The model is based on simple integrate and fire neurons and facilitates an on-line learning. The whole system, including the hardware required to build (evolve) the network was hosted on one FPGA chip. The implementation used 45% of the logic elements, 76% of the memory, and 23% of the dedicated multiplier slices of the chip. FPGA size was sufficient for 64 neurons with up to 64 synapses each (a total of 4096 synapses). The proposed FPGA implementation was successfully applied to a classification problem of taste recognition and the FPGA implementation was at least 10 times faster when evolving the network and 74 times faster during the classification than the software simulations executed by a stand-alone PC.

show abstract

Section: Introductionmentioning

confidence: 99%

FPGA Implementation of an Evolving Spiking Neural Network

Zuppicich

Soltic

2009

Advances in Neuro-Information Processing

View full text Add to dashboard Cite

show abstract

“…Floreano and collaborators devised a multi-cellular reconfigurable circuit capable of evolution, self-repair, and adaptation [102] and used it as a substrate for evolving spiking controllers of a wheeled robot [103]. Although evolved hardware controllers are not widely used in evolutionary robotics, they still hold out the promise of some very useful properties, such as robustness to faults, which make them interesting for extreme condition applications such as space robotics.…”

Section: Evolvable Hardware Robot Controllersmentioning

confidence: 99%

Evolutionary Robotics

Floreano

Husbands

Nolfi

2008

Springer Handbook of Robotics

127

View full text Add to dashboard Cite

“…This neural model is well suited for compact hardware implementation [69]. 10 In all of the experiments of this section the population is composed of 50 individuals.…”

Section: Originalmentioning

confidence: 99%

“…Evolution with the morphogenetic system with 16 diffusers and 12 entries in the expression table (one for each type of neuron) is compared to a direct genetic encoding. The size of the morphogenetic 10 More complex neural models capable of learning can also be evolved with the morphogenetic system [69]. …”

Section: Originalmentioning

confidence: 99%

Evolutionary morphogenesis for multi-cellular systems

Roggen

Federici

Floreano

2006

Genet Program Evolvable Mach

View full text Add to dashboard Cite

With a gene required for each phenotypic trait, direct genetic encodings may show poor scalability to increasing phenotype length. Developmental systems may alleviate this problem by providing more efficient indirect genotype to phenotype mappings. A novel classification of multi-cellular developmental systems in evolvable hardware is introduced. It shows a category of developmental systems that up to now has rarely been explored. We argue that this category is where most of the benefits of developmental systems lie (e.g. speed, scalability, robustness, inter-cellular and environmental interactions that allow fault-tolerance or adaptivity). This article describes a very simple genetic encoding and developmental system designed for multi-cellular circuits that belongs to this category. We refer to it as the morphogenetic system. The morphogenetic system is inspired by gene expression and cellular differentiation. It focuses on low computational requirements which allows fast execution and a compact hardware implementation. The morphogenetic system shows better scalability compared to a direct genetic encoding in the evolution of structures of differentiated cells, and its dynamics provides fault-tolerance up to high fault rates. It outperforms a direct genetic encoding when evolving spiking neural networks for

show abstract

Hardware spiking neural network with run-time reconfigurable connectivity in an autonomous robot

Abstract: Abstract

Cited by 51 publications

References 24 publications

FPGA Implementation of an Evolving Spiking Neural Network

FPGA Implementation of an Evolving Spiking Neural Network

Evolutionary Robotics

Evolutionary morphogenesis for multi-cellular systems

Contact Info

Product

Resources

About