Abstract
The Tsetlin Machine (TM) constitutes an emerging machine learning algorithm that has shown competitive performance on several benchmarks. The underlying concept of the TM is propositional logic determined by a group of finite state machines that learns patterns. Thus, TM-based systems naturally lend themselves to low-power operation when implemented in hardware for micro-edge Internet-of-Things applications. An important aspect of the learning phase of TMs is stochasticity. For low-power integrated circuit implementations the random number generation must be carried out efficiently. In this paper, we explore the application of pre-generated cyclostationary random number sequences for TMs. Through experiments on two machine learning problems, i.e., Binary Iris and Noisy XOR, we demonstrate that the accuracy is on par with standard TM. We show that through exploratory simulations the required length of the sequences that meets the conflicting tradeoffs can be suitably identified. Furthermore, the TMs achieve robust performance against reduced resolution of the random numbers. Finally, we show that maximum-length sequences implemented by linear feedback shift registers are suitable for generating the required random numbers.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abeyrathna, K.D., Granmo, O.C., Goodwin, M.: Extending the Tsetlin machine with integer-weighted clauses for increased interpretability. IEEE Access 9, 8233–8248 (2021). https://ieeexplore.ieee.org/document/9316190
Abeyrathna, K.D., et al.: A Multi-Step Finite-State Automaton for Arbitrarily Deterministic Tsetlin Machine Learning. Expert Systems, John Wiley & Sons Ltd., Hoboken (2021). https://doi.org/10.1111/exsy.12836
Abeyrathna, K.D., et al.: Massively parallel and asynchronous tsetlin machine architecture supporting almost constant-time scaling. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 10–20. PMLR, 18–24 July 2021. https://proceedings.mlr.press/v139/abeyrathna21a.html
Bajaj, N.: Nikeshbajaj/linear_feedback_shift_register: 1.0.6, April 2021. https://doi.org/10.5281/zenodo.4726667
C library function - rand(): https://www.tutorialspoint.com/c_standard_library/c_function_rand.htm
Granmo, O.C.: Github TM repo. https://github.com/cair/TsetlinMachine
Granmo, O.C.: The Tsetlin machine–a game theoretic bandit driven approach to optimal pattern recognition with propositional logic. arXiv e-prints (2018). https://arxiv.org/abs/1804.01508
Granmo, O.C., Glimsdal, S., Jiao, L., Goodwin, M., Omlin, C.W., Berge, G.T.: The convolutional Tsetlin machine. arXiv e-prints (2019). https://arxiv.org/abs/1905.09688
Haykin, S.: Communication Systems, 4th edn. John Wiley & Sons, Inc., Hoboken (2001)
Numpy library. https://www.numpy.org
Partow, A.: https://www.partow.net/programming/polynomials/index.html
Python 3.10.0 doc.: http://docs.python.org/3/library/random.html
Rahman, T., Shafik, R., Granmo, O.C., Yakovlev, A.: Resilient biomedical systems design under noise using logic based machine learning. Front. Control Eng. (in press, 2022). Adaptive, Robust and Fault Tolerant Control. https://www.frontiersin.org/articles/10.3389/fcteg.2021.778118/abstract
Sarwate, D., Pursley, M.: Crosscorrelation properties of pseudorandom and related sequences. Proc. IEEE 68(5), 593–619 (1980)
Sharma, J., Yadav, R., Granmo, O.C., Jiao, L.: Human interpretable AI: Enhancing Tsetlin machine stochasticity with drop clause. arXiv (2021). https://arxiv.org/abs/2105.14506
UCI Machine Learning Repo. https://archive.ics.uci.edu/ml/datasets/iris
Wheeldon, A., Shafik, R., Rahman, T., Lei, J., Yakovlev, A., Granmo, O.C.: Learning automata based energy-efficient AI hardware design for IoT applications: learning automata based AI hardware. Royal Society Publishing (2020). https://doi.org/10.1098/rsta.2019.0593
Zhang, X., Jiao, L., Granmo, O.C., Goodwin, M.: On the convergence of tsetlin machines for the identity-and not operators. IEEE Trans. Pattern Anal. Mach. Intell. (2021). https://doi.org/10.1109/TPAMI.2021.3085591
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Tunheim, S.A., Yadav, R.K., Jiao, L., Shafik, R., Granmo, OC. (2022). Cyclostationary Random Number Sequences for the Tsetlin Machine. In: Fujita, H., Fournier-Viger, P., Ali, M., Wang, Y. (eds) Advances and Trends in Artificial Intelligence. Theory and Practices in Artificial Intelligence. IEA/AIE 2022. Lecture Notes in Computer Science(), vol 13343. Springer, Cham. https://doi.org/10.1007/978-3-031-08530-7_71
Download citation
DOI: https://doi.org/10.1007/978-3-031-08530-7_71
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08529-1
Online ISBN: 978-3-031-08530-7
eBook Packages: Computer ScienceComputer Science (R0)