| On the Reduction of Computational Complexity of Deep Convolutional Neural Networks P Maji, R Mullins Entropy, 2018 | 55 | 2018 |
| Efficient winograd or cook-toom convolution kernel implementation on widely used mobile cpus P Maji, A Mundy, G Dasika, J Beu, M Mattina, R Mullins 2019 2nd Workshop on Energy Efficient Machine Learning and Cognitive …, 2019 | 36 | 2019 |
| An analytical performance model for the Spidergon NoC with virtual channels M Moadeli, A Shahrabi, W Vanderbauwhede, P Maji Journal of Systems Architecture 56 (1), 16-26, 2010 | 22 | 2010 |
| Apparatus and method for providing a bidirectional communications link between a master device and a slave device P MAJI, SR Mellor, ARM Limited US Patent App. 13/439,171, 2012 | 21* | 2012 |
| Stochastic-yolo: Efficient probabilistic object detection under dataset shifts T Azevedo, R de Jong, M Mattina, P Maji arXiv preprint arXiv:2009.02967, 2020 | 17 | 2020 |
| Quarc: A High-Efficiency network on-Chip architecture M Moadeli, P Maji, W Vanderbauwhede Advanced Information Networking and Applications, 2009. AINA'09 …, 2009 | 17 | 2009 |
| ADaPT: optimizing CNN inference on IoT and mobile devices using approximately separable 1-D kernels P Maji, D Bates, A Chadwick, R Mullins Proceedings of the 1st International Conference on Internet of Things and …, 2017 | 12 | 2017 |
| Design and implementation of the Quarc Network on-Chip M Moadeli, PP Maji, W Vanderbauwhede Parallel & Distributed Processing, 2009. IPDPS 2009. IEEE International …, 2009 | 9 | 2009 |
| Design and implementation of the Quarc Network on-Chip P Maji, M Moadeli, W Vanderbauwhede Parallel & Distributed Processing, 2009. IPDPS 2009. IEEE International …, 2009 | 9* | 2009 |
| 1D-FALCON: Accelerating deep convolutional neural network inference by co-optimization of models and underlying arithmetic implementation P Maji, R Mullins Artificial Neural Networks and Machine Learning–ICANN 2017: 26th …, 2017 | 8 | 2017 |
| On the effects of quantisation on model uncertainty in bayesian neural networks M Ferianc, P Maji, M Mattina, M Rodrigues Uncertainty in Artificial Intelligence, 929-938, 2021 | 7 | 2021 |
| Stochastic-shield: A probabilistic approach towards training-free adversarial defense in quantized cnns L Qendro, S Ha, R de Jong, P Maji Proceedings of the 1st Workshop on Security and Privacy for Mobile AI, 1-6, 2021 | 7 | 2021 |
| Towards efficient point cloud graph neural networks through architectural simplification SA Tailor, R de Jong, T Azevedo, M Mattina, P Maji Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 7 | 2021 |
| On efficient uncertainty estimation for resource-constrained mobile applications J Rock, T Azevedo, R de Jong, D Ruiz-Muñoz, P Maji arXiv preprint arXiv:2111.09838, 2021 | 4 | 2021 |
| Data packet flow control across an asynchronous clock domain boundary P MAJI, SR Mellor, ARM Limited US Patent 8,630,358, 2014 | 3 | 2014 |
| Tinyops: Imagenet scale deep learning on microcontrollers S Sadiq, J Hare, P Maji, S Craske, GV Merrett Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 2 | 2022 |
| Deff-arts: Differentiable efficient architecture search S Sadiq, P Maji, J Hare, G Merrett | 2 | 2020 |
| An underexplored dilemma between confidence and calibration in quantized neural networks G Xia, S Ha, T Azevedo, P Maji arXiv preprint arXiv:2111.08163, 2021 | 1 | 2021 |
| Object Detection Network with Spatial Uncertainty P Prasun, TML Azevedo US Patent App. 17/179,806, 2022 | | 2022 |
Robert MullinsDepartment of Computer Science and Technology, University of CambridgeVerified email at cl.cam.ac.uk
