Optimizing MNIST Digit Recognition for Edge Devices: A Multi-dimensional Evaluation Approach
DOI:
https://doi.org/10.46610/JAHNMC.2026.v03i02.003Keywords:
Edge Computing, Lightweight CNN, MNIST, Model Optimization, TinyMLAbstract
Handwritten digit recognition on the MNIST dataset routinely achieves near-perfect accuracy. However, deploying these models on edge platforms introduces new challenges where predictive accuracy is no longer the only metric that matters. For constrained systems, memory footprint, computational overhead, and inference latency are equally critical. In this work, they propose a multi-dimensional evaluation framework for deployment-oriented assessment. The authors introduce the Edge Suitability Score (ESS), a composite metric that combines normalized accuracy, model size, and inference speed into a single value, weighted at 0.40, 0.35, and 0.25, respectively, to reflect their relative importance for microcontroller deployment. By comparing two lightweight architectures, a scaled-down CNN (L-CNN) and a depthwise-separable L-MobileNet, against a deeper Baseline CNN, the results show that compact networks can maintain near-99% accuracy while drastically reducing storage and computation requirements: L-MobileNet achieves 99.10% accuracy with only 12,186 parameters and roughly 48 KB of weight memory, compared with 99.45% accuracy and over 1 MB for the baseline. This framework offers a practical methodology for selecting neural networks in real-world edge environments, bridging the gap between theoretical performance and actual deployability on resource-constrained hardware such as the STM32 and ESP32.
References
W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, “Edge Computing: Vision and Challenges,” IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637–646, Oct. 2016.
H. Han and J. Siebert, “TinyML: A Systematic Review and Synthesis of Existing Research,” 2022 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 269–274, Feb. 2022.
P. Warden and D. Situnayake, “TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-low-power Microcontrollers.” O'reilly, 2019.
N. Suda et al., “Throughput-Optimized OpenCL-based FPGA Accelerator for Large-Scale Convolutional Neural Networks,” Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 16–25, Feb. 2016.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, May 2012.
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-Based Learning Applied to Document Recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 2018.
S. Sabour, N. Frosst, and G. E. Hinton, “Dynamic Routing Between Capsules,” Curran Associates, Inc., 2017.
A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, Apr. 17, 2017.
F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “SqueezeNet: AlexNet-level Accuracy with 50X Fewer Parameters and <0.5MB model size, arXiv:1602.07360, Nov. 2016.
M. Tan and Q. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Mingxing Tan, Quoc Le, Proceedings of the 36th International Conference on Machine Learning, pp. 6105–6114, May 2019.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510–4520, Jun. 2018.
X. Zhang, X. Zhou, M. Lin, and J. Sun, “ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848–6856, Jun. 2018.
P. P. Ray, “A Review on TinyML: State-of-the-Art and Prospects,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 4, pp. 1595–1623, Apr. 2022.
R. David et al., “TensorFlow Lite Micro: Embedded Machine Learning for TinyML Systems,” Proceedings of Machine Learning and Systems, vol. 3, pp. 800–811, Mar. 2021.
L. Dutta and S. Bharali, “TinyML Meets IoT: A Comprehensive Survey,” Internet of Things, vol. 16, pp. 100461, Oct. 2021.
S. Han, H. Mao, and W. J. Dally, “Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding,” arXiv:1510.00149, Feb. 2016.
B. Jacob and S. Kligys, “Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026.
H. Cai, L. Zhu, and S. Han, “ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware,” arXiv.org. Aug, 2026.
C. Banbury et al., “MLPerf Tiny Benchmark,” arXiv:2106.07597v4, Jun. 2021.
D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, Dec. 22, 2014.
J. Lin, W.-M. Chen, Y. Lin, cohn, G. Chuang, and S. Han, “MCUNet: Tiny Deep Learning on IoT Devices,” Advances in Neural Information Processing Systems, vol. 33, pp. 11711–11722, 2020.
