Dolly Sapra

Latest

• ARM-CO-UP: ARM COoperative Utilization of Processors
• The paper 'FAA+RTS: Designing Fault-Aware Adaptive Real-Time Systems - From Specification to Execution' was accepted at SAMOS '24.
• The paper 'PiQi: Partially Quantized DNN Inference on HMPSoCs' was accepted at ACM/IEEE ISLPED 2024.
• The paper 'ARM-CO-UP: ARM COoperative Utilization of Processors' was accepted for publication in the ACM Transactions on Design Automation of Electronic Systems.
• PiQi: Partially Quantized DNN Inference on HMPSoCs
• The demo/tool 'ARM-CO-UP: ARM Co-Operative Utilization of Processors' was accepted for the Embedded Systems Software Competition at the IEEE/ACM Embedded Systems Week 2023.
• The paper 'PELSI: Power-Efficient Layer-Switched Inference' has been nominated for the Best Paper Award at IEEE RTCSA '23!
• The paper 'PELSI: Power-Efficient Layer-Switched Inference' was accepted for publication at IEEE RTCSA '23.
• The paper 'On Achieving Privacy-Preserving State-of-the-Art Edge Intelligence' was accepted at PPAI 2023.
• Edge AI
• The paper 'CPU-GPU Layer-Switched Low Latency CNN Inference' was accepted for Euromicro DSD 2022.
• Designing convolutional neural networks with constrained evolutionary piecemeal training
• The paper 'Scenario Based Run-time Switching for Adaptive CNN-based Applications at the Edge' was accepted for ACM Transactions on Embedded Computing Systems.
• Designing convolutional neural networks with constrained evolutionary piecemeal training
• The paper 'The Choice of AI Matters: Alternative Machine Learning Approaches for CPS Anomalies' was accepted for IEA/AIE 2021.
• The paper 'Deep Learning Model Reuse and Composition in Knowledge Centric Networking’ was accepted for ICCCN 2020.
• The paper 'An Evolutionary Optimization Algorithm for Gradually Saturating Objective Functions’ was accepted for ACM GECCO 2020.
• The paper 'Constrained Evolutionary Piecemeal Training to Design Efficient Neural Networks’ was accepted for IEA/AIE 2020.
• An evolutionary optimization algorithm for gradually saturating objective functions
• Constrained Evolutionary Piecemeal Training to Design Convolutional Neural Networks
• Deep Learning Model Reuse and Composition in Knowledge Centric Networking
• Optimization and deployment of CNNs at the Edge: The ALOHA experience