NeMo: A Platform for Neural Modelling of Spiking Neurons Using GPUs

Fidjeland, Andreas K.; Roesch, Etienne B.; Shanahan, Murray; Luk, Wayne

doi:10.1109/asap.2009.24

Cited by 86 publications

(67 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current implementation of the network is computationally costly (several seconds of processing time are required per arm movement). In future work, we aim to implement the proposed network using our GPU architecture [19] in order to achieve real-time performance.…”

Section: Discussionmentioning

confidence: 99%

Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity

Bouganis

Shanahan

2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-In this paper, we present a spiking neural network architecture that autonomously learns to control a 4 degree-offreedom robotic arm after an initial period of motor babbling. Its aim is to provide the joint commands that will move the end-effector in a desired spatial direction, given the joint configuration of the arm. The spiking neurons have been simulated according to Izhikevich's model, which exhibits biologically realistic behaviour and yet is computationally efficient. The architecture is a feed-forward network where the input layers encode the intended movement direction of the end-effector in spatial coordinates, as well as the information that is given by proprioception about the current joint angles of the arm. The motor commands are determined by decoding the firing patterns in the output layers. Both excitatory and inhibitory synapses connect the input and output layers, and their initial weights are set to random values. The network learns to map input stimuli to motor commands during a phase of repetitive action-perception cycles, in which Spike Timing-Dependent Plasticity (STDP) strengthens synapses between neurons that are correlated and weakens synapses between uncorrelated ones. The trained spiking neural network has been successfully tested on a kinematic model of the arm of an iCub humanoid robot.

show abstract

Section: Discussionmentioning

confidence: 99%

Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity

Bouganis

Shanahan

2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…Here, network activity clustering like in (Fidjeland et al, 2009) may help scale the networks further. This would also be an promising approach for dividing large scale simulations over multiple GPUs.…”

Section: Discussionmentioning

confidence: 99%

“…A number of e↵orts have focused on developing e cient GPU-based simulation algorithms for specific di↵erential-based spiking neuron models like the Hodgkin-Huxley model (Lazar and Zhou, 2012;Mutch et al, 2010), or variants of integrate-and-fire spiking neurons, like the Izhikevich model (Brette and Goodman, 2011;Fidjeland et al, 2009;Fidjeland and Shanahan, 2010;Han and Taha, 2010a,b;Krishnamani and Venkittaraman, 2010;Nageswaran et al, 2008;Vekterli, 2009;Yudanov, 2009;Yudanov et al, 2010). The advantage of di↵erential-based spiking neuron models is that the parameters describing the neural state tend to be few, and evolving neural dynamics can be computed from the di↵erential equations.…”

mentioning

confidence: 99%

Streaming parallel GPU acceleration of large-scale filter-based spiking neural networks

Slazynski

Bohté

2012

Network: Computation in Neural Systems

View full text Add to dashboard Cite

The arrival of graphics processing (GPU) cards suitable for massively parallel computing promises a↵ordable large-scale neural network simulation previously only available at supercomputing facilities. While the raw numbers suggest that GPUs may outperform CPUs by at least an order of magnitude, the challenge is to develop fine-grained parallel algorithms to fully exploit the particulars of GPUs. Computation in a neural network is inherently parallel and thus a natural match for GPU architectures: given inputs, the internal state for each neuron can be updated in parallel. We show that for filter-based spiking neurons, like the Spike Response Model, the additive nature of membrane potential dynamics enables additional update parallelism. This also reduces the accumulation of numerical errors when using single precision computation, the native precision of GPUs. We further show that optimizing simulation algorithms and data structures to the GPU's architecture has a large pay-o↵: for example, matching iterative neural updating to the memory architecture of the GPU speeds up this simulation step by a factor of three to five. With such optimizations, we can simulate in better-than-realtime plausible spiking neural networks of up to 50,000 neurons, processing over 35 million spiking events per second.

show abstract

“…Fidjeland et al [7] presented a real-time implementation of IZ-based SNN for the cluster-oriented network topologies. No verification with reference implementation is performed.…”

Section: Introductionmentioning

confidence: 99%

GPU-based simulation of spiking neural networks with real-time performance & high accuracy

Yudanov

Shaaban

Melton

et al. 2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

A novel GPU-based simulation of spiking neural networks is implemented as a hybrid system using ParkerSochacki numerical integration method with adaptive order. Full single-precision floating-point accuracy for all model variables is achieved. The implementation is validated with exact matching of all neuron potential traces from GPU-based simulation versus those of a reference CPU-based simulation. A network of 4096 Izhikevich neurons simulated on an NVIDIA GTX260 device achieves real-time performance with a speedup of 9 compared to simulation executed on Opteron 285, 2.6-GHz device.Index Terms-GPU, CUDA, STDP, spiking neural network, high accuracy, parallel computing, shared memory.

show abstract

NeMo: A Platform for Neural Modelling of Spiking Neurons Using GPUs

Cited by 86 publications

References 18 publications

Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity

Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity

Streaming parallel GPU acceleration of large-scale filter-based spiking neural networks

GPU-based simulation of spiking neural networks with real-time performance & high accuracy

Contact Info

Product

Resources

About

NeMo: A Platform for Neural Modelling of Spiking Neurons Using GPUs

Cited by 86 publications

References 18 publications

Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity

Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity

Streaming parallel GPU acceleration of large-scale filter-based spiking neural networks

GPU-based simulation of spiking neural networks with real-time performance &amp; high accuracy

Contact Info

Product

Resources

About

GPU-based simulation of spiking neural networks with real-time performance & high accuracy