Authors

Faiqua Rizwan

Physics Department, Shibli National College, Azamgarh-India

Priyanjala Yadav

Physics Department, Shibli National College, Azamgarh-India

Shikha Yadav

Physics Department, Shibli National College, Azamgarh-India

Mohd. Imran Aziz

Physics Department, Shibli National College, Azamgarh-India

Abstract

Traditional neural networks struggle to generalize arithmetic operations beyond the numerical range seen   during   training. This paper investigates the implementation and evaluation of a Neural Arithmetic Logic Unit (NALU).A specialized neural network module introduced in the paper AI-Driven Arithmetic Logic Units, designed to improve numerical reasoning and arithmetic generalization. The NALU architecture extends the Neural Accumulator (NAC) by incorporating both additive and multiplicative computation pathways, controlled by a learnable gating mechanism. This structure enables the model to learn exact arithmetic operations such as addition, subtraction, multiplication, and division, while maintaining the ability to extrapolate beyond the training range. In this manuscript, the NALU model was implemented using TensorFlow and evaluated on synthetic arithmetic tasks.

Keywords

Neural Networks Artificial Neural Network Tensor Flow Logic Gates

Citation of this Article

Faiqua Rizwan, Priyanjala Yadav, Shikha Yadav, & Mohd. Imran Aziz. (2026). AI-Driven Arithmetic Logic Units. Journal of Artificial Intelligence and Emerging Technologies (JAIET). 3(4), 42-48. Article DOI: https://doi.org/10.47001/JAIET/2026.304006

Licence Copyright (c) 2026 Journal of Artificial Intelligence and Emerging Technologies. This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International Licence.

References

  1. Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra,C  Lawrence Zitnick, and Devi Parikh. VQA: Visual question answering. In Proceedings of the IEEE International Conference on Computer Vision, pages 2425–2433, 2015.
  2. Carlos Arteta, Victor Lempitsky, J Alison Noble, and Andrew Zisserman. Interactive object counting. In European Conference on Computer Vision, pages 504–518, 2014.
  3. Steven L Brunton, Joshua L Proctor, and J Nathan Kutz. Discovering governing equations from data by sparse identification of nonlinear dynamical systems. Proceedings of the National Academy of Sciences, 113(15):3932–3937, 2016.
  4. Antoni B Chan, Zhang-Sheng John Liang, and Nuno Vasconcelos. Privacy preserving crowd monitoring: Counting people without people models or tracking. In Proc. CVPR, pages 1–7 IEEE, 2008.
  5. Stanislas Dehaene. The Number Sense: How the Mind Creates Mathematics. Oxford University Press, 2011.
  6. Jerry A. Fodor and Zenon W. Pylyshyn. Connectionism and cognitive architecture: a critical analysis. Cognition, 28(1–2):3–71, 1988.
  7. C. Randy Gallistel. Finding numbers in the brain. Philosophical Transactions of the Royal Society B, 373, 2017.
  8. Rochel Gelman and C. Randy Gallistel. The child’s understanding of number. Harvard, 1978.
  9. Felix A Gers and E Schmidhuber. LSTM recurrent networks learn simple context-free and context-sensitive languages. IEEE Transactions on Neural Networks, 12(6):1333–1340, 2001.
  10. Alex Graves, Abdel-rahman Mohamed, and Geoffrey Hinton. Speech recognition with deep recurrent neural networks. In Acoustics, speech and signal processing (ICASSP), 2013 IEEE international conference on, pages 6645–6649. IEEE, 2013.
  11. Alex Graves, Greg Wayne, and Ivo Danihelka. Neural Turing machines. CoRR, abs/1410.5401, 2014. URL http://arxiv.org/abs/1410.5401.
  12. Alex Graves, Greg Wayne, Malcolm Reynolds, Tim Harley, Ivo Danihelka, Agnieszka Grabska- Barwi´nska, Sergio Gómez Colmenarejo, Edward Grefenstette, Tiago Ramalho, John Agapiou, et al. Hybrid computing using a neural network with dynamic external memory. Nature, 538 (7626):471, 2016.
  13. Edward Grefenstette, Karl Moritz Hermann, Mustafa Suleyman, and Phil Blunsom. Learning to transduce with unbounded memory. In Proc. NIPS, 2015.
  14. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Identity mappings in deep residual networks. CoRR, abs/1603.05027, 2016. URL http://arxiv.org/abs/1603.05027.
  15. Gao Huang, Zhuang Liu, and Kilian Q. Weinberger. Densely connected convolutional networks. CoRR, abs/1608.06993, 2016. URL http://arxiv.org/abs/1608.06993.
  16. Rafal Jozefowicz, Oriol Vinyals, Mike Schuster, Noam Shazeer, and Yonghui Wu. Exploring the limits of language modeling. arXiv preprint arXiv:1602.02410, 2016.
  17. Alex Krizhevsky and Geoff Hinton. Convolutional deep belief networks on CIFAR-10. Unpub- lished manuscript, 2010.
  18. Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, and Richard Socher. Ask me anything: Dynamic memory networks for natural language processing. In Proc. ICML, pages 1378–1387, 2016.
  19. Brendan Lake and Marco Baroni. Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks. In Proc. ICML, 2018.
  20. Gary F. Marcus. The Algebraic Mind: Integrating Connectionism and Cognitive Science. MIT Press, 2003.
  21. Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lilli- crap, Tim Harley, David Silver, and Koray Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In Proc. ICML, pages 1928–1937, 2016.
  22. Manuela Piazza, Véronique Izard, Philippe Pinel, Denis Le Bihan, and Stanislas Dehaene. Tuning curves for approximate numerosity in the human intraparietal sulcus. Neuron, 44: 547–555, 2004.
  23. Scott E. Reed and Nando de Freitas. Neural programmer-interpreters. In Proc. ICLR, 2016.
  24. David E. Rumelhart, Geoffrey E. Hinton, and Ronald J. Williams. Learning representations by back-propagating errors. Nature, 323(6088):533, 1986.
  25. Santi Seguí, Oriol Pujol, and Jordi Vitrià. Learning to count with deep object features. CoRR, abs/1505.08082, 2015. URL http://arxiv.org/abs/1505.08082.