Neuroevolution of Spiking Neural Networks Using Compositional Pattern Producing Networks

Elbrecht, Daniel; Schuman, Catherine

doi:10.1145/3407197.3407198

Title: Neuroevolution of Spiking Neural Networks Using Compositional Pattern Producing Networks

Full Record
Other Related Research

Abstract

Spiking neural networks (SNNs) offer tremendous potential for the future of AI, including the ability to be implemented efficiently on neuromorphic systems. One of the challenges in building functioning SNNs is the training process, as standard error back-propagation cannot be easily applied. In this work, we extend an evolutionary approach for training SNNs by implementing an indirect encoding of individuals. Specifically, we evolve SNNs using Compositional Pattern Producing Networks, which are able to learn the connectivity patterns between neurons defined in a coordinate space. We validate the approach on multiple control and classification tasks.

Authors:

^[1];

^[1]

ORNL

Publication Date:: 2020-07-01

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

OSTI Identifier:: 1649077

DOE Contract Number:: AC05-00OR22725

Resource Type:: Conference

Resource Relation:: Conference: International Conference on Neuromorphic Systems (ICONS) - Oak Ridge, Tennessee, United States of America - 7/28/2020 8:00:00 AM-7/30/2020 8:00:00 AM

Country of Publication:: United States

Language:: English

Citation Formats


                    Elbrecht, Daniel, and Schuman, Catherine. Neuroevolution of Spiking Neural Networks Using Compositional Pattern Producing Networks.  United States: N. p., 2020. 
        Web.  doi:10.1145/3407197.3407198.

Copy to clipboard


                    Elbrecht, Daniel, & Schuman, Catherine. Neuroevolution of Spiking Neural Networks Using Compositional Pattern Producing Networks.  United States.  https://doi.org/10.1145/3407197.3407198

Copy to clipboard


                    Elbrecht, Daniel, and Schuman, Catherine. 2020.  
        "Neuroevolution of Spiking Neural Networks Using Compositional Pattern Producing Networks".  United States.  https://doi.org/10.1145/3407197.3407198.  https://www.osti.gov/servlets/purl/1649077.

Copy to clipboard


                    
@article{osti_1649077,

  title        = {Neuroevolution of Spiking Neural Networks Using Compositional Pattern Producing Networks},

  author       = {Elbrecht, Daniel and Schuman, Catherine},

  abstractNote = {Spiking neural networks (SNNs) offer tremendous potential for the future of AI, including the ability to be implemented efficiently on neuromorphic systems. One of the challenges in building functioning SNNs is the training process, as standard error back-propagation cannot be easily applied. In this work, we extend an evolutionary approach for training SNNs by implementing an indirect encoding of individuals. Specifically, we evolve SNNs using Compositional Pattern Producing Networks, which are able to learn the connectivity patterns between neurons defined in a coordinate space. We validate the approach on multiple control and classification tasks.},

  doi          = {10.1145/3407197.3407198},

  url          = {https://www.osti.gov/biblio/1649077},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2020},

  month        = {7}

}

Copy to clipboard

Conference:

View Conference (0.51 MB)

https://doi.org/10.1145/3407197.3407198

Other availability

Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Energy Efficient Stochastic-Based Deep Spiking Neural Networks for Sparse Datasets

Conference Alawad, Mohammed; Yoon, Hong-Jun; Tourassi, Georgia

With large deep neural networks (DNNs) neces- sary to solve complex and data-intensive problems, energy efficiency is a key bottleneck for effectively deploying DL in the real world. Deep spiking NNs have gained much research at- tention recently due to the interest in building biological neural networks and the availability of neuromorphic platforms, which can be orders of magnitude more energy efficient compared to CPUs and GPUs. Although spiking NNs have proven to be an efficient technique for solving many machine learning and computer vision problems, to the best of our knowledge, this is the first attempt to adapt spikingmore »« less
https://doi.org/10.1109/BigData.2017.8257939

Full Text Available
Multi-Objective Hyperparameter Optimization for Spiking Neural Network Neuroevolution

Conference Parsa, Maryam; Kulkarni, Shruti; Coletti, Mark; ...

Neuroevolution has had significant success over recent years, but there has been relatively little work applying neuroevolution approaches to spiking neural networks (SNNs). SNNs are a type of neural network that includes temporal processing component, are not easily trained using other methods, and can be deployed into energy-efficient neuromorphic hardware. In this work, we investigate two evolutionary approaches for training SNNs. We explore the impact of the hyperparameters of the evolutionary approaches, including tournament size, population size, and representation type, on the performance of the algorithms. We present a multi-objective Bayesian-based hyperparameter optimization approach to tune the hyperparameters to producemore »« less
Full Text Available
Training Spiking Neural Networks with Synaptic Plasticity under Integer Representation

Conference Kulkarni, Shruti; Parsa, Maryam; Mitchell, Parker; ...

Neuromorphic computing is emerging as a promising Beyond Moore computing paradigm that employs event-triggered computation and non-von Neumann hardware. Spike Timing Dependent Plasticity (STDP) is a well-known bio-inspired learning rule that relies on activities of locally connected neurons to adjust the weights of their respective synapses. In this work, we analyze a basic STDP rule and its sensitivity on the different hyperparameters for training spiking neural networks (SNNs) with supervision, customized for a neuromorphic hardware implementation with integer weights. We compare the classification performance on four UCI datasets (iris, wine, breast cancer and digits) that depict varying levels of complexity.more »« less
https://doi.org/10.1145/3477145.3477152

Full Text Available
Dilute Combustion Control Using Spiking Neural Networks

Journal Article Maldonado Puente, Bryan; Kaul, Brian; Schuman, Catherine; ... - SAE Technical Paper Series

Dilute combustion with exhaust gas recirculation (EGR) in spark-ignition engines presents a cost-effective method for achieving higher levels of engine efficiency. At high levels of EGR, however, cycle-to-cycle variability (CCV) of the combustion process is exacerbated by sporadic occurrences of misfires and partial burns. Previous studies have shown that temporal deterministic patterns emerge at such conditions and certain combustion cycles have a significant influence over future events. Due to the complexity of the combustion process and the nature of CCV, harnessing all the deterministic information for control purposes has remained challenging even with physics based 0-D, 1-D, and high-fidelity computationalmore »« less
https://doi.org/10.4271/2021-01-0534

Full Text Available
Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks

Conference Dimovska, Mihaela; Johnston, Travis; Schuman, Catherine; ...

Inspired by the connectivity mechanisms in the brain, neuromorphic computing architectures model Spiking Neural Networks (SNNs) in silicon. As such, neuromorphic architectures are designed and developed with the goal of having small, low power chips that can perform control and machine learning tasks. However, the power consumption of the developed hardware can greatly depend on the size of the network that is being evaluated on the chip. Furthermore, the accuracy of a trained SNN that is evaluated on chip can change due to voltage and current variations in the hardware that perturb the learned weights of the network. While effortsmore »« less
https://doi.org/10.1109/UEMCON47517.2019.8992983

Full Text Available

Similar Records