دسته بندی:
اینترنت اشیاء - Internet of Things
سال انتشار:
2022
عنوان انگلیسی مقاله:
Resource efficient AI: Exploring neural network pruning for task specialization
ترجمه فارسی عنوان مقاله:
هوش مصنوعی کارآمد منابع: بررسی هرس شبکه عصبی برای تخصص در کار
منبع:
ScienceDirect- Elsevier- Internet of Things, 20 (2022) 100599: doi:10:1016/j:iot:2022:100599
نویسنده:
Dieter Balemans
چکیده انگلیسی:
This paper explores the use of neural network pruning for transfer learning applications for more
resource-efficient inference. The goal is to focus and optimize a neural network on a smaller
specialized target task. With the advent of IoT, we have seen an immense increase in AI-based
applications on mobile and embedded devices, such as wearables and other smart appliances.
However, with the ever-increasing complexity and capabilities of machine learning algorithms,
this push to the edge has led to new challenges due to the constraints imposed by the limited
availability of resources on these devices. Some form of compression is needed to allow for stateof-the-art convolutional neural networks to run on edge devices. In this work, we adapt existing
neural network pruning methods to allow them to specialize networks to only focus on a subset
of what they were originally trained for. This is a transfer learning use-case where we optimize
large pre-trained networks. This differs from standard optimization techniques by allowing the
network to forget certain concepts and allow the network’s footprint to be even smaller. We
compare different pruning criteria, including one from the field of Explainable AI (XAI), to
determine which technique allows for the smallest possible network while maintaining high
performance on the target task. Our results show the benefits of using network specialization
when executing neural networks on embedded devices both with and without GPU acceleration.
keywords: فشرده سازی شبکه عصبی | یادگیری ماشین | هوش مصنوعی قابل توضیح | هرس شبکه عصبی | استنتاج لبه | Neural network compression | Machine learning | Explainable AI | Neural network pruning | Edge inference
قیمت: رایگان
توضیحات اضافی:
تعداد نظرات : 0