ABSTRACT
The emergence of embedded machine learning has enabled the migration of intelligence from the cloud to the edge and to the sensors. To explore the practicalities of wide-spread deployments of these intelligent sensors, we look beyond traditional arithmetic-based neural networks (NNs) to the logic-based learning algorithm called the Tsetlin Machine (TM). TMs have not yet been implemented and explored on general purpose microcontrollers especially that are intermittently powered. In this paper, we argue that their simple architecture makes them a promising candidate for batteryless ML systems. However, in their current form, they are not suitable to be deployed on resource-constrained sensors because of the substantial memory footprint of trained models. To tackle this issue, we propose a lossless compression scheme based on run-length encoding and evaluate against standard TMs for vision and acoustic workloads. We show that our encoding can compress the model by up to 99% without accuracy loss. This translates into lower memory footprint and better energy efficiency (up to 4.9x) compared to the original Tsetlin Machine algorithm, and provides promising trade offs when compared against binary neural networks.
- Omid Ardakanian, Arka Bhattacharya, and David Culler. 2016. Non-intrusive techniques for establishing occupancy related energy savings in commercial buildings. In Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments. 21--30.Google ScholarDigital Library
- Abu Bakar, Alexander G Ross, Kasim Sinan Yildirim, and Josiah Hester. 2021. REHASH: A Flexible, Developer Focused, Heuristic Adaptation Platform for Intermittently Powered Computing. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 5, 3 (2021), 1--42.Google ScholarDigital Library
- Domenico Balsamo, Alex S Weddell, Geoff V Merrett, Bashir M Al-Hashimi, Davide Brunelli, and Luca Benini. 2014. Hibernus: Sustaining computation during intermittent supply for energy-harvesting systems. IEEE Embedded Systems Letters 7, 1 (2014), 15--18.Google ScholarDigital Library
- Gregory Chen, Hassan Ghaed, Razi-ul Haque, Michael Wieckowski, Yejoong Kim, Gyouho Kim, David Fick, Daeyeon Kim, Mingoo Seok, Kensall Wise, et al. 2011. A cubic-millimeter energy-autonomous wireless intraocular pressure monitor. In 2011 IEEE International Solid-State Circuits Conference. IEEE, 310--312.Google ScholarCross Ref
- Andy Rosales Elias, Nevena Golubovic, Chandra Krintz, and Rich Wolski. 2017. Where's the bear? Automating wildlife image processing using iot and edge cloud systems. In 2017 IEEE/ACM Second International Conference on Internet-of-Things Design and Implementation (IoTDI). IEEE, 247--258.Google Scholar
- LeCun et al. 1998. The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/. Accessed: 10-21-2021.Google Scholar
- Graham Gobieski, Brandon Lucia, and Nathan Beckmann. 2019. Intelligence beyond the edge: Inference on intermittent embedded systems. In Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems. 199--213.Google ScholarDigital Library
- Ole-Christoffer Granmo. 2018. The Tsetlin Machine--A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic. arXiv preprint arXiv:1804.01508 (2018).Google Scholar
- Josiah Hester and Jacob Sorber. 2017. The future of sensing is batteryless, intermittent, and awesome. In Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems.Google ScholarDigital Library
- Bashima Islam and Shahriar Nirjon. 2019. Zygarde: Time-sensitive on-device deep inference and adaptation on intermittently-powered systems. arXiv preprint arXiv:1905.03854 (2019).Google Scholar
- Vito Kortbeek, Abu Bakar, Stefany Cruz, Kasim Sinan Yildirim, Przemysław Pawełczak, and Josiah Hester. 2020a. Bfree: Enabling battery-free sensor prototyping with python. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 4 (2020), 1--39.Google ScholarDigital Library
- Vito Kortbeek, Kasim Sinan Yildirim, Abu Bakar, Jacob Sorber, Josiah Hester, and Przemysław Pawełczak. 2020b. Time-sensitive intermittent computing meets legacy software. In Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems. 85--99.Google ScholarDigital Library
- Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. (2009).Google Scholar
- Jie Lei, Tousif Rahman, Rishad Shafik, Adrian Wheeldon, Alex Yakovlev, Ole-Christoffer Granmo, Fahim Kawsar, and Akhil Mathur. 2021. Low-power audio keyword spotting using Tsetlin machines. Journal of Low Power Electronics and Applications 11, 2 (2021), 18.Google ScholarCross Ref
- Brandon Lucia, Vignesh Balaji, Alexei Colin, Kiwan Maeng, and Emily Ruppel. 2017. Intermittent computing: Challenges and opportunities. In 2nd Summit on Advances in Programming Languages (SNAPL 2017). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik.Google Scholar
- Kiwan Maeng, Alexei Colin, and Brandon Lucia. 2017. Alpaca: Intermittent execution without checkpoints. Proceedings of the ACM on Programming Languages 1, OOPSLA (2017), 1--30.Google ScholarDigital Library
- Bradley McDanel, Surat Teerapittayanon, and HT Kung. 2017. Embedded binarized neural networks. arXiv preprint arXiv:1709.02260 (2017).Google Scholar
- Alessandro Montanari, Mohammed Alloulah, and Fahim Kawsar. 2019. Degradable inference for energy autonomous vision applications. In Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers. 592--597.Google ScholarDigital Library
- Alessandro Montanari, Manuja Sharma, Dainius Jenkus, Mohammed Alloulah, Lorena Qendro, and Fahim Kawsar. 2020. ePerceptive: energy reactive embedded intelligence for batteryless sensors. In Proceedings of the 18th Conference on Embedded Networked Sensor Systems. 382--394.Google ScholarDigital Library
- Matteo Nardello, Harsh Desai, Davide Brunelli, and Brandon Lucia. 2019. Camaroptera: A batteryless long-range remote visual sensing system. In Proceedings of the 7th International Workshop on Energy Harvesting & Energy-Neutral Sensing Systems. 8--14.Google ScholarDigital Library
- Philip Sparks. 2017. The route to a trillion devices. White Paper, ARM.Google Scholar
- Pete Warden. 2018. Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209 (2018).Google Scholar
- Adrian Wheeldon, Rishad Shafik, Tousif Rahman, Jie Lei, Alex Yakovlev, and Ole-Christoffer Granmo. 2020. Learning automata based energy-efficient AI hardware design for IoT applications. Philosophical Transactions of the Royal Society A 378, 2182 (2020), 20190593.Google Scholar
- Kasım Sinan Yıldırım, Amjad Yousef Majid, Dimitris Patoukas, Koen Schaper, Przemyslaw Pawelczak, and Josiah Hester. 2018. Ink: Reactive kernel for tiny batteryless sensors. In Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems. 41--53.Google ScholarDigital Library
Index Terms
- Logic-based intelligence for batteryless sensors
Recommendations
Adaptive Intelligence for Batteryless Sensors Using Software-Accelerated Tsetlin Machines
SenSys '22: Proceedings of the 20th ACM Conference on Embedded Networked Sensor SystemsTsetlin Machine (TM) is a new machine learning algorithm that encodes propositional logic into learning automata---a set of logical expressions composed of boolean input features---to recognise patterns. The simplicity, efficiency, and accuracy of this ...
Timely Execution on Intermittently Powered Batteryless Sensors
SenSys '17: Proceedings of the 15th ACM Conference on Embedded Network Sensor SystemsTiny intermittently powered computers can monitor objects in hard to reach places maintenance free for decades by leaving batteries behind and surviving off energy harvested from the environment--- avoiding the cost of replacing and disposing of ...
Energy consumption forecasting based on Elman neural networks with evolutive optimization
One new method is proposed based on recurrent neural networks.The method addresses the problem of energy consumption forecasting.The method is evaluated using data form public buildings of University of Granada. Buildings are an essential part of our ...
Comments