To defray the increasingly massive costs of running large machine learning workloads, much work has proposed running them on preemptible cloud instances, a discount tier of virtual machine rentals that may be interrup...
详细信息
(1)Artificial intelligence is becoming increasingly popular for IoT applications in safety-critical fields (e.g., autonomous systems and biomedical, robots). Unfortunately, the inference's workload process alone i...
详细信息
ISBN:
(纸本)9798350370560;9798350370553
(1)Artificial intelligence is becoming increasingly popular for IoT applications in safety-critical fields (e.g., autonomous systems and biomedical, robots). Unfortunately, the inference's workload process alone increases as the model size grows. To meet the computational power limitations of mobile devices running IoT applications, modern services sometimes resort to the Split Computing paradigm. Split Computing divides the inference process of a Neural Network into Head and Tail for their execution in a mobile device and a server, respectively, which also allows the reduction of the overall IoT device's computational cost. Nonetheless, Split Computing can be used in safety-critical fields where reliability is crucial, especially when mobile devices have computational and cost restrictions. This paper introduces hardening techniques acting on the software to mitigate the effects of hardware faults on Split Computing models. The proposed hardening techniques consist of i) a bounded activation function whose thresholds are refined by training, and ii) a per-channel bounding of the bottleneck quantization of the split points. To quantitatively assess their effectiveness, we resorted to two different split configurations of a model for image classification. In addition, we considered a Split Computing model for object detection. Our findings indicate that the proposed approaches effectively reduces fault effects by 3.5% for image classifiers and 5.73% for object detectors when compared with other hardening approaches for general DNNs.
This article proposes a new Artificial Intelligent (AI) and Machine Learning (ML) based framework for 6G-enabled Intelligent edge computing. The framework will be equipped with multiple cognitive controllers to harmon...
详细信息
distributed networked systems form an essential resource for computation and applications ranging from commercial, military, scientific, and research communities. Allocation of resources on a given infrastructure is r...
详细信息
ISBN:
(数字)9781665497268
ISBN:
(纸本)9781665497268
distributed networked systems form an essential resource for computation and applications ranging from commercial, military, scientific, and research communities. Allocation of resources on a given infrastructure is realized through various mapping systems that are tailored towards specific use cases of the requesting applications. While HPC system requests demand compute resources heavy on processor and memory, cloud applications may demand distributed web services that are composed of networked processing and some memory. All resource requests allocate on the infrastructure with some form of network connectivity. However, during mapping of resources, the features and topology constraints of network components are typically handled indirectly through abstractions of user requests. This paper is on a novel graph representation that enables precise mapping methods for distributed networked systems. The proposed graph representations are demonstrated to allocate specific network components and adjacency requirements of a requested graph on a given infrastructure. Furthermore, we report on application of business policy requirements that resulted in increased utilization and a gradual decrease in idle node count as requests are mapped using our proposed methods.
Spiking neural networks (SNNs), as biologically inspired computational models, possess significant advantages in energy efficiency due to their event-driven operations. However, challenges remain in attaining high com...
详细信息
The DRM (Digital Rights Management) systems protect owners' copyrights by controlling consumers' access to digital works. However, they fail to provide authorization evidence if customers use digital works on ...
详细信息
Software-Defined networks (SDN) is a technology that separates the data plane from the control plane, garnering significant interest from researchers in universities and companies. SDN enables network engineers to con...
详细信息
In general, the popularity of DDoS attacks being used as a weapon to harm the opposite party, is on the rise. Hence, is the need for the security from such disruptive attacks. There have been several attempts at detec...
详细信息
Deep learning is of great importance for studies in the field of natural language processing. Question Answering (QA) systems, which are widely used today, are one of these studies. QA studies are concerned with the a...
详细信息
Approximate neighbour nearest search has achieved great success for indexing similar high-dimensional data in distributed search systems. As the scale of data vectors grows, distributed search require large storage, l...
详细信息
暂无评论