On-device STDP and synaptic normalization for neuromemristive spiking neural network

Soures, Nicholas; Hays, Lydia; Bohannon, Eric; Zyarah, Abdullah M.; Kudithipudi, Dhireesha

doi:10.1109/mwscas.2017.8053115

Cited by 6 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first model combines Leaky Integrate and Fire (LIF) neurons with a simple step-wise STDP function (see below). Such a learning rule is also quite common and similar concepts can be found in various works about the SORN model Lazar et al (2009) or other works like Masquelier and Thorpe (2007), Rolls (2010), Stocco et al (2010), Soures et al (2017), Tomasello et al (2018), or Gautam and Kohno (2021) to name some examples. The second one is a more conventional model consisting of the Izhikevich neuron model combined with a standard widely used trace STDP rule (Song et al, 2000;Cohen et al, 2007;Galluppi et al, 2015;Qiao et al, 2019).…”

Section: Introductionmentioning

confidence: 90%

Accelerating spiking neural network simulations with PymoNNto and PymoNNtorch

Vieth,

Rahimi,

Gorgan Mohammadi

et al. 2024

Front. Neuroinform.

View full text Add to dashboard Cite

Spiking neural network simulations are a central tool in Computational Neuroscience, Artificial Intelligence, and Neuromorphic Engineering research. A broad range of simulators and software frameworks for such simulations exist with different target application areas. Among these, PymoNNto is a recent Python-based toolbox for spiking neural network simulations that emphasizes the embedding of custom code in a modular and flexible way. While PymoNNto already supports GPU implementations, its backend relies on NumPy operations. Here we introduce PymoNNtorch, which is natively implemented with PyTorch while retaining PymoNNto's modular design. Furthermore, we demonstrate how changes to the implementations of common network operations in combination with PymoNNtorch's native GPU support can offer speed-up over conventional simulators like NEST, ANNarchy, and Brian 2 in certain situations. Overall, we show how PymoNNto's modular and flexible design in combination with PymoNNtorch's GPU acceleration and optimized indexing operations facilitate research and development of spiking neural networks in the Python programming language.

show abstract

Section: Introductionmentioning

confidence: 90%

Accelerating spiking neural network simulations with PymoNNto and PymoNNtorch

Vieth,

Rahimi,

Gorgan Mohammadi

et al. 2024

Front. Neuroinform.

View full text Add to dashboard Cite

show abstract

“…However, infusing hybrid plasticity mechanisms such as short-term plasticity or long-term synaptic plasticity can help enhance the computational performance. It is interesting to note that the reservoir computational models (both spiking and non-spiking) seem to have a boost in their performance from embedding intrinsic plasticity, akin to the biological models [42,43]. This convergence with the biological counterparts vastly improves our understanding of building spatiotemporal processing, though one should take a parsimonious approach with correlations.…”

Section: Neural Mappingmentioning

confidence: 99%

Analysis of Wide and Deep Echo State Networks for Multiscale Spatiotemporal Time Series Forecasting

Carmichael

Syed

Kudithipudi

2019

Proceedings of the 7th Annual Neuro-Inspired Computational Elements Workshop

Self Cite

View full text Add to dashboard Cite

Echo state networks are computationally lightweight reservoir models inspired by the random projections observed in cortical circuitry. As interest in reservoir computing has grown, networks have become deeper and more intricate. While these networks are increasingly applied to nontrivial forecasting tasks, there is a need for comprehensive performance analysis of deep reservoirs. In this work, we study the influence of partitioning neurons given a budget and the effect of parallel reservoir pathways across different datasets exhibiting multi-scale and nonlinear dynamics.

show abstract

“…The first function of the local controller is to initialize the memristor crossbar with the random weights and then apply synaptic scaling to ensure an average homogeneous excitability. Utilizing Ziksa to enable SS was demonstrated in (9). The second function of Ziksa in the reservoir layer is to implement STP.…”

Section: Reservoir Layermentioning

confidence: 99%

(Invited) Enabling On-Device Learning with Deep Spiking Neural Networks for Speech Recognition

et al. 2018

View full text Add to dashboard Cite

Spiking recurrent neural networks are gaining traction in solving complex temporal tasks. In general, spiking neural networks are resilient and computationally powerful. These intrinsic properties make them attractive for learning on edge devices. In this work, we propose a semi-supervised deep spiking neural network (deep-liquid state machine) that can be deployed on embedded devices. We demonstrate a high-level memristor based neuromorphic architecture for the proposed deep spiking network. An experimental TiN-TaOx-TaTiN memristor device stack model is used for analyzing the overall architecture performance. An accuracy of 95.83 +/-1.74% is achieved for a speech recognition task, on the standard TIMIT dataset. To study the robustness of the proposed architecture, the accuracy of the network was tested with and without noise in the memristor devices.

show abstract

On-device STDP and synaptic normalization for neuromemristive spiking neural network

Cited by 6 publications

References 14 publications

Accelerating spiking neural network simulations with PymoNNto and PymoNNtorch

Accelerating spiking neural network simulations with PymoNNto and PymoNNtorch

Analysis of Wide and Deep Echo State Networks for Multiscale Spatiotemporal Time Series Forecasting

(Invited) Enabling On-Device Learning with Deep Spiking Neural Networks for Speech Recognition

Contact Info

Product

Resources

About