Survey: Exploiting data redundancy for optimization of deep learning
Data redundancy is ubiquitous in the inputs and intermediate results of Deep Neural
Networks (DNN). It offers many significant opportunities for improving DNN performance and …
Networks (DNN). It offers many significant opportunities for improving DNN performance and …
Machine learning in real-time Internet of Things (IoT) systems: A survey
Over the last decade, machine learning (ML) and deep learning (DL) algorithms have
significantly evolved and been employed in diverse applications, such as computer vision …
significantly evolved and been employed in diverse applications, such as computer vision …
Lalarand: Flexible layer-by-layer cpu/gpu scheduling for real-time dnn tasks
Deep neural networks (DNNs) have shown remarkable success in various machine-learning
(ML) tasks useful for many safety-critical, real-time embedded systems. The foremost design …
(ML) tasks useful for many safety-critical, real-time embedded systems. The foremost design …
On removing algorithmic priority inversion from mission-critical machine inference pipelines
The paper discusses algorithmic priority inversion in mission-critical machine inference
pipelines used in modern neural-network-based cyber-physical applications, and develops …
pipelines used in modern neural-network-based cyber-physical applications, and develops …
Zygarde: Time-sensitive on-device deep inference and adaptation on intermittently-powered systems
We propose Zygarde--which is an energy--and accuracy-aware soft real-time task
scheduling framework for batteryless systems that flexibly execute deep learning tasks1 that …
scheduling framework for batteryless systems that flexibly execute deep learning tasks1 that …
R-TOD: Real-time object detector with minimized end-to-end delay for autonomous driving
For realizing safe autonomous driving, the end-to-end delays of real-time object detection
systems should be thoroughly analyzed and minimized. However, despite recent …
systems should be thoroughly analyzed and minimized. However, despite recent …
Jellyfish: Timely inference serving for dynamic edge networks
While high accuracy is of paramount importance for deep learning (DL) inference, serving
inference requests on time is equally critical but has not been carefully studied especially …
inference requests on time is equally critical but has not been carefully studied especially …
Kairos: Building cost-efficient machine learning inference systems with heterogeneous cloud resources
Online inference is becoming a key service product for many businesses, deployed in cloud
platforms to meet customer demands. Despite their revenue-generation capability, these …
platforms to meet customer demands. Despite their revenue-generation capability, these …
Real-time task scheduling for machine perception in intelligent cyber-physical systems
This paper explores criticality-based real-time scheduling of neural-network-based machine
inference pipelines in cyber-physical systems (CPS) to mitigate the effect of algorithmic …
inference pipelines in cyber-physical systems (CPS) to mitigate the effect of algorithmic …
Self-cueing real-time attention scheduling in criticality-aware visual machine perception
This paper presents a self-cueing real-time frame-work for attention prioritization in AI-
enabled visual perception systems that minimizes a notion of state uncertainty. By attention …
enabled visual perception systems that minimizes a notion of state uncertainty. By attention …