DNNs, commonly employed for complex tasks such as image and language processing, are increasingly sought for deployment on Internet of Things (IoT) devices. These devices operate with constrained resources, including limited computational power, memory, slower processors, and restricted energy requirements. Consequently, optimizing DNN models becomes crucial to minimize memory usage and computational time. However, traditional optimization methods require skilled professionals to manually fine-tune hyperparameters, striking a balance between efficiency and accuracy. This paper introduces an innovative solution for identifying optimal hyperparameters, focusing on the application of pruning, clusterization, and quantization.


Giovannesi, L., Proietti Mattia, G., & Beraldi, R. (2024). Targeted and Automatic Deep Neural Networks Optimization for Edge Computing. In L. Barolli (Ed.), Advanced Information Networking and Applications (pp. 57–68). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-57931-8_6

  title = {Targeted and Automatic Deep Neural Networks Optimization for Edge Computing},
  author = {Giovannesi, Luca and Proietti Mattia, Gabriele and Beraldi, Roberto},
  year = {2024},
  booktitle = {Advanced Information Networking and Applications},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  pages = {57--68},
  doi = {10.1007/978-3-031-57931-8_6},
  isbn = {978-3-031-57931-8},
  editor = {Barolli, Leonard}