Ensembles of CNNs represent an effective aggregation strategy to improve accuracy. Nevertheless, The use of multiple CNN models increases memory and computing requirements, thus limiting the applicability of this approach in edge devices. We hence propose a methodology to address this challenge by constructing Embedded Ensembles of CNNs (E2CNN). Our proposal combines pruning and replication to transform an input single-instance CNN into an equivalent ensemble-based architecture. The resulting model benefits the higher accuracy and robustness of state-of-the-art ensembles, without increasing the initial memory and computing requirements. |
| Using Algorithmic Transformations and Sensitivity Analysis to Unleash Approximations in CNNs at the Edge |
| Ponzina, Flavio; Ansaloni, Giovanni; Peon Quiros, Miguel; Atienza Alonso, David |
| 2022-07-19 | MDPI Micromachines - Special Issue "Hardware-Friendly Machine Learning and Its Applications" | |  |  |  |  |
| Error Resilient In-Memory Computing Architecture for CNN Inference on the Edge |
| Rios, Marco Antonio; Ponzina, Flavio; Ansaloni, Giovanni; Levisse, Alexandre Sébastien Julien; Atienza Alonso, David |
| 2022-06-07 | Proceedings of the Great Lakes Symposium on VLSI 2022 | | | | | |
| An Accuracy-Driven Compression Methodology to Derive Efficient Codebook-Based CNNs |
| Ponzina, Flavio; Ansaloni, Giovanni; Peon Quiros, Miguel; Atienza Alonso, David |
| 2022 | Conference Paper | | | | |
| A hardware/software co-design vision for deep learning at the edge |
| Ponzina, Flavio; Machetti, Simone; Rios, Marco Antonio; Denkinger, Benoît Walter; Levisse, Alexandre Sébastien Julien; Ansaloni, Giovanni; Peon Quiros, Miguel; Atienza Alonso, David |
| 2022 | IEEE Micro - Special Issue on Artificial Intelligence at the Edge | | | | |
| A Flexible In-Memory Computing Architecture for Heterogeneously Quantized CNNs |
| Ponzina, Flavio; Rios, Marco Antonio; Ansaloni, Giovanni; Levisse, Alexandre Sébastien Julien; Atienza Alonso, David |
| 2021-07-07 | 2021 IEEE Computer Society Annual Symposium on VLSI (ISVLSI) | | | | |
| E2CNN: Ensembles of Convolutional Neural Networks to Improve Robustness Against Memory Errors in Edge-Computing Devices |
| Ponzina, Flavio; Peon Quiros, Miguel; Burg, Andreas Peter; Atienza Alonso, David |
| 2021 | IEEE - Transactions on Computers | | | | |
