Abstract
Training large-scale neural network models is computationally expensive and demands a great deal of resources. It is an important area of study with a lot of potential for the future of the AI industry. In recent years, the power of computer hardware has significantly improved and we have new breakthroughs in deep learning. With these innovations, the computational cost of training large neural network models has declined by at least 10 folds in high- and average-performance machines. In this research, we explore NAL, AutoML, and other frameworks to determine the best suitable model for edge devices. The biggest improvements compared to reference models can be acquired if the NAS algorithm is co-designed with the corresponding inference engine.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Banbury, C., et al.: MicroNets: neural network architectures for deploying TinyML applications on commodity microcontrollers (2020)
Cai, H., Gan, C., Han, S.: Once for all: train one network and specialize it for efficient deployment. arXiv, pp. 1–15 (2019)
Cai, H., Zhu, L., Han, S.: ProxylessNAS: direct neural architecture search on target task and hardware. arXiv, pp. 1–13 (2018)
Chu, X., Zhang, B., Xu, R., Li, J.: FairNAS: rethinking evaluation fairness of weight sharing neural architecture search (2019)
David, R., et al.: TensorFlow Lite Micro: embedded machine learning on TinyML systems (2020)
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a LargeScale hierarchical image database. In: CVPR 2009 (2009)
Fedorov, I., Adams, R.P., Mattina, M., Whatmough, P.N.: SpArSe: sparse architecture search for CNNs on resource-constrained microcontrollers. arXiv, pp. 1–26 (2019)
Geada, R., Prangle, D., McGough, A.S.: Bonsai-Net: Oneshot Neural Architecture Search via differentiable pruners (2020)
He, X., Zhao, K., Chu, X.: AutoML: a survey of the state-of-the Art. arXiv, (Dl) (2019)
Krizhevsky, A., Nair, V., Hinton, G.: Cifar-10 (Canadian Institute for Advanced Research)
Lai, L., Suda, N., Chandra, V.: CMSIS-NN: efficient neural network Kernels for arm cortex-M CPUs. arXiv, pp. 1–10 (2018)
Liberis, E., Dudziak, L., Lane, N.D.: µNAS: constrained neural architecture search for microcontrollers (2020)
Liberis, E., Lane, N.D.: Neural networks on microcontrollers: saving memory at inference via operator reordering. arXiv, pp. 1–8 (2019)
Lin, J., Chen, W.-M., Lin, Y., Cohn, J., Gan, C., Han, S.: MCUNet: tiny deep learning on IoT devices. (NeurIPS), pp. 1–12 (2020)
Liu, D., Kong, H., Luo, X., Liu, W., Subramaniam, R.: Bringing AI to edge: from deep learning’s perspective, pp. 1–23 (2020)
Molchanov, P., Mallya, A., Tyree, S., Frosio, I., Kautz, J.: Importance estimation for neural network pruning. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2019)
Rusci, M., Capotondi, A., Benini, L.: Memory-driven mixed low precision quantization for enabling deep network inference on microcontrollers. arXiv (2019)
Rusci, M., Fariselli, M., Capotondi, A., Benini, L.: Leveraging automated mixed-low-precision quantization for tiny edge microcontrollers. arXiv, pp. 1–12 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Singh, B., Mansukhani, J. (2023). Comparing Neural Architectures to Find the Best Model Suited for Edge Devices. In: Sharma, H., Saha, A.K., Prasad, M. (eds) Proceedings of International Conference on Intelligent Vision and Computing (ICIVC 2022). ICIVC 2022. Proceedings in Adaptation, Learning and Optimization, vol 17. Springer, Cham. https://doi.org/10.1007/978-3-031-31164-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-31164-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31163-5
Online ISBN: 978-3-031-31164-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)