ABSTRACT
Evolutionary algorithms have been shown to be an effective method for training (or configuring) spiking neural networks. There are, however, challenges to developing accessible, scalable, and portable solutions. We present an extension to the Fugu framework that wraps the NEAT framework, bringing evolutionary algorithms to Fugu. This approach provides a flexible and customizable platform for optimizing network architectures, independent of fitness functions and input data structures. We leverage Fugu's computational graph approach to evaluate all members of a population in parallel. Additionally, as Fugu is platform-agnostic, this population can be evaluated in simulation or on neuromorphic hardware. We demonstrate our extension using several classification and agent-based tasks. One task illustrates how Fugu integration allows for spiking pre-processing to lower the search space dimensionality. We also provide some benchmark results using the Intel Loihi platform.
- Dimitris Achlioptas. 2003. Database-friendly random projections: Johnson-Lindenstrauss with binary coins. Journal of computer and System Sciences 66, 4 (2003), 671--687.Google ScholarDigital Library
- James Aimone, Prasanna Date, Gabriel Fonseca-Guerra, Kathleen Hamilton, Kyle Henke, Bill Kay, Garrett Kenyon, Shruti Kulkarni, Susan Mniszewski, Maryam Parsa, et al. 2022. A review of non-cognitive applications for neuromorphic computing. Neuromorphic Computing and Engineering (2022).Google Scholar
- James B Aimone, Aaron J Hill, William M Severa, and Craig M Vineyard. 2021. Spiking Neural Streaming Binary Arithmetic. In 2021 International Conference on Rebooting Computing (ICRC). IEEE, 79--83.Google Scholar
- James B Aimone, Yang Ho, Ojas Parekh, Cynthia A Phillips, Ali Pinar, William Severa, and Yipu Wang. 2021. Provable advantages for graph algorithms in spiking neural networks. In Proceedings of the 33rd ACM Symposium on Parallelism in Algorithms and Architectures. 35--47.Google ScholarDigital Library
- James B Aimone, William Severa, and Craig M Vineyard. 2019. Composing neural algorithms with Fugu. In Proceedings of the International Conference on Neuromorphic Systems. 1--8.Google ScholarDigital Library
- Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. 2019. Optuna: A Next-generation Hyperparameter Optimization Framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Google ScholarDigital Library
- Mike Davies, Narayan Srinivasa, Tsung-Han Lin, Gautham Chinya, Yongqiang Cao, Sri Harsha Choday, Georgios Dimou, Prasad Joshi, Nabil Imam, Shweta Jain, et al. 2018. Loihi: A neuromorphic manycore processor with on-chip learning. Ieee Micro 38, 1 (2018), 82--99.Google ScholarCross Ref
- Robert P Dick, Rob Aitken, Jace Mogill, John Paul Strachan, Kirk Bresniker, Wei Lu, Yorie Nakahira, Zhiyong Li, Matthew J Marinella, William Severa, et al. 2023. Research Challenges for Energy-Efficient Computing in Automated Vehicles. Computer 56, 3 (2023), 47--58.Google ScholarDigital Library
- Ronald A Fisher. 1936. The use of multiple measurements in taxonomic problems. Annals of eugenics 7, 2 (1936), 179--188.Google ScholarCross Ref
- David Ha. 2017. A Visual Guide to Evolution Strategies. blog.otoro.net (2017). https://blog.otoro.net/2017/10/29/visual-evolution-strategies/Google Scholar
- Oliver Kramer and Oliver Kramer. 2016. Scikit-learn. Machine learning for evolution strategies (2016), 45--53.Google ScholarCross Ref
- Jeffrey L Krichmar, William Severa, Muhammad S Khan, and James L Olds. 2019. Making BREAD: Biomimetic strategies for artificial intelligence now and in the future. Frontiers in neuroscience 13 (2019), 666.Google Scholar
- Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018).Google Scholar
- Wolfgang Maass, Thomas Natschläger, and Henry Markram. 2002. Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural computation 14, 11 (2002), 2531--2560.Google Scholar
- Alan McIntyre, Matt Kallada, Cesar G. Miguel, Carolina Feher de Silva, and Marcio Lobo Netto. [n. d.]. neat-python.Google Scholar
- Ryan Melzer, William M Severa, Mark Plagge, and Craig M Vineyard. 2021. Exploring characteristics of neural network architecture computation for enabling SAR ATR. In Automatic Target Recognition XXXI, Vol. 11729. SPIE, 42--61.Google Scholar
- Garrick Orchard, E Paxon Frady, Daniel Ben Dayan Rubin, Sophia Sanborn, Sumit Bam Shrestha, Friedrich T Sommer, and Mike Davies. 2021. Efficient neuromorphic signal processing with loihi 2. In 2021 IEEE Workshop on Signal Processing Systems (SiPS). IEEE, 254--259.Google ScholarCross Ref
- Robert Patton, Catherine Schuman, Shruti Kulkarni, Maryam Parsa, J Parker Mitchell, N Quentin Haas, Christopher Stahl, Spencer Paulissen, Prasanna Date, Thomas Potok, et al. 2021. Neuromorphic computing for autonomous racing. In International Conference on Neuromorphic Systems 2021. 1--5.Google ScholarDigital Library
- NG Pavlidis, OK Tasoulis, Vassilis P Plagianakos, G Nikiforidis, and MN Vrahatis. 2005. Spiking neural network training using evolutionary algorithms. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005., Vol. 4. IEEE, 2190--2194.Google ScholarCross Ref
- Yiming Peng, Gang Chen, Harman Singh, and Mengjie Zhang. 2018. NEAT for Large-Scale Reinforcement Learning through Evolutionary Feature Learning and Policy Gradient Search. In Proceedings of the Genetic and Evolutionary Computation Conference (Kyoto, Japan) (GECCO '18). Association for Computing Machinery, New York, NY, USA, 490--497. Google ScholarDigital Library
- John JM Reynolds, James S Plank, Catherine D Schuman, Grant R Bruer, Adam W Disney, Mark E Dean, and Garrett S Rose. 2018. A comparison of neuromorphic classification tasks. In Proceedings of the International Conference on Neuromorphic Systems. 1--8.Google ScholarDigital Library
- Charles P Rizzo, Catherine D Schuman, and James S Plank. 2023. Neuromorphic Downsampling of Event-Based Camera Output. In Neuro-Inspired Computational Elements Conference. 26--34.Google Scholar
- Tim Salimans, Jonathan Ho, Xi Chen, Szymon Sidor, and Ilya Sutskever. 2017. Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint arXiv:1703.03864 (2017).Google Scholar
- Yulia Sandamirskaya, Mohsen Kaboli, Jorg Conradt, and Tansu Celikel. 2022. Neuromorphic computing hardware and neural architectures for robotics. Science Robotics 7, 67 (2022), eabl8419.Google Scholar
- Catherine Schuman, Charles Rizzo, John McDonald-Carmack, Nicholas Skuda, and James Plank. 2022. Evaluating encoding and decoding approaches for spiking neuromorphic systems. In Proceedings of the International Conference on Neuromorphic Systems 2022. 1--9.Google ScholarDigital Library
- Catherine D Schuman, J Parker Mitchell, Robert M Patton, Thomas E Potok, and James S Plank. 2020. Evolutionary optimization for neuromorphic systems. In Proceedings of the Neuro-inspired Computational Elements Workshop. 1--9.Google ScholarDigital Library
- Catherine D Schuman, James S Plank, Adam Disney, and John Reynolds. 2016. An evolutionary optimization framework for neural networks and neuromorphic architectures. In 2016 International Joint Conference on Neural Networks (IJCNN). IEEE, 145--154.Google ScholarCross Ref
- William Severa, Craig M Vineyard, Ryan Dellana, Stephen J Verzi, and James B Aimone. 2019. Training deep neural networks for binary communication with the whetstone method. Nature Machine Intelligence 1, 2 (2019), 86--94.Google ScholarCross Ref
- Sumit B Shrestha and Garrick Orchard. 2018. Slayer: Spike layer error reassignment in time. Advances in neural information processing systems 31 (2018).Google Scholar
- J Darby Smith, William Severa, Aaron J Hill, Leah Reeder, Brian Franke, Richard B Lehoucq, Ojas D Parekh, and James B Aimone. 2020. Solving a steady-state PDE using spiking networks and neuromorphic hardware. In International Conference on Neuromorphic Systems 2020. 1--8.Google ScholarDigital Library
- Kenneth O Stanley and Risto Miikkulainen. 2002. Efficient evolution of neural network topologies. In Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No. 02TH8600), Vol. 2. IEEE, 1757--1762.Google ScholarCross Ref
- Felipe Petroski Such, Vashisht Madhavan, Edoardo Conti, Joel Lehman, Kenneth O Stanley, and Jeff Clune. 2017. Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. arXiv preprint arXiv:1712.06567 (2017).Google Scholar
- Amirhossein Tavanaei, Masoud Ghodrati, Saeed Reza Kheradpisheh, Timothée Masquelier, and Anthony Maida. 2019. Deep learning in spiking neural networks. Neural networks 111 (2019), 47--63.Google Scholar
- Craig Vineyard, Suma Cardwell, Frances Chance, Srideep Musuvathy, Fred Rothganger, William Severa, John Smith, Corinne Teeter, Felix Wang, and James Aimone. 2022. Neural Mini-Apps as a Tool for Neuromorphic Computing Insight. In Neuro-Inspired Computational Elements Conference. 40--49.Google ScholarDigital Library
- Craig Vineyard, William Severa, Matthew Kagie, Andrew Scholand, and Park Hays. 2019. A Resurgence in Neuromorphic Architectures Enabling Remote Sensing Computation. In 2019 IEEE Space Computing Conference (SCC). IEEE, 33--40.Google ScholarCross Ref
- Felix Wang. 2015. Simulation tool for asynchronous cortical streams (STACS): interfacing with spiking neural networks. Procedia Computer Science 61 (2015), 322--327.Google ScholarCross Ref
- Benjamin Ward-Cherrier, Nicholas Pestell, and Nathan F Lepora. 2020. Neurotac: A neuromorphic optical tactile sensor applied to texture recognition. In 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2654--2660.Google ScholarCross Ref
Index Terms
- Neuromorphic Population Evaluation using the Fugu Framework
Recommendations
Algorithm and Application Impacts of Programmable Plasticity in Spiking Neuromorphic Hardware
ICONS '23: Proceedings of the 2023 International Conference on Neuromorphic SystemsSynaptic plasticity has long been thought to be key to learning in both biological neural networks and artificial neural networks. There are a wide array of plasticity rules in biological neural systems, but neuromorphic computing has mainly focused ...
Design space exploration and parameter tuning for neuromorphic applications
CODES+ISSS '13: Proceedings of the Ninth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System SynthesisLarge-scale spiking neural networks (SNNs) have been used to successfully model complex neural circuits that explore various neural phenomena such as learning and memory, vision systems, auditory systems, neural oscillations, and many other important ...
Context-Dependent Computations in Spiking Neural Networks with Apical Modulation
Artificial Neural Networks and Machine Learning – ICANN 2023AbstractNeocortical pyramidal neurons integrate two distinct streams of information. Bottom-up information arrives at their basal dendrites, and resulting neuronal activity is modulated by top-down input that targets the apical tufts of these neurons and ...
Comments