Deep Learning Optimization for Edge Devices: Analysis of Training Quantization Parameters

Kwaśniewska, Alicja; Szankin, Maciej; Ozga, Mateusz; Wolfe, J. P.; Das, Arun; Zając, Adam; Rumiński, Jacek; Rad, Paul

doi:10.1109/iecon.2019.8927153

Cited by 12 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Successful use of DL algorithms in healthcare [1]- [3], ophthalmology [4]- [6], developmental disorders [7]- [9], in autonomous robots and vehicles [10]- [12], in image processing classification and detection [13], [14], in speech and audio processing [15], [16], cyber-security [17], [18], and many more indicate the reach of DL algorithms in our daily lives. Easier access to high-performance compute nodes using cloud computing ecosystems, high-throughput AI accelerators to enhance performance, and access to big-data scale datasets and storage enables deep learning providers to research, test, and operate ML algorithms at scale in small edge devices [19], smartphones [20], and AI-based web-services using Application Programming Interfaces (APIs) for wider exposure to any applications.…”

Section: Introductionmentioning

confidence: 99%

Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey

Das,

Rad

2020

Preprint

Self Cite

177

187

View full text Add to dashboard Cite

Nowadays, deep neural networks are widely used in mission critical systems such as healthcare, self-driving vehicles, and military which have direct impact on human lives. However, the black-box nature of deep neural networks challenges its use in mission critical applications, raising ethical and judicial concerns inducing lack of trust. Explainable Artificial Intelligence (XAI) is a field of Artificial Intelligence (AI) that promotes a set of tools, techniques, and algorithms that can generate high-quality interpretable, intuitive, human-understandable explanations of AI decisions. In addition to providing a holistic view of the current XAI landscape in deep learning, this paper provides mathematical summaries of seminal work. We start by proposing a taxonomy and categorizing the XAI techniques based on their scope of explanations, methodology behind the algorithms, and explanation level or usage which helps build trustworthy, interpretable, and self-explanatory deep learning models. We then describe the main principles used in XAI research and present the historical timeline for landmark studies in XAI from 2007 to 2020. After explaining each category of algorithms and approaches in detail, we then evaluate the explanation maps generated by eight XAI algorithms on image data, discuss the limitations of this approach, and provide potential future directions to improve XAI evaluation.

show abstract

Section: Introductionmentioning

confidence: 99%

Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey

Das,

Rad

2020

Preprint

Self Cite

177

187

View full text Add to dashboard Cite

show abstract

“…However, the training and inference stages of deep learning neural networks are limited by the space of the memory and a variety of factors, including programming complexity and even the reliability of the system. The process of quantization has become increasingly popular due to the significant impact on performance and minimal accuracy loss [220]. Furthermore, to ensure that local SE decisions are synchronized with minimum time delay, dynamic models that are trained online will be indispensable.…”

Section: B Deployment Of Advanced ML Solutionsmentioning

confidence: 99%

Self-Evolving Integrated Vertical Heterogeneous Networks

Farajzadeh

Khoshkholgh²,

Yanıkömeroğlu

et al. 2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

“…However, the training and inference stages of deep learning neural networks are limited by the space of the memory and a variety of factors, including programming complexity and even reliability of the system. On the whole the process of quantization has become increasingly popular due to the significant impact on performance and minimal accuracy loss [147]. Furthermore, to ensure that local SE decisions are synchronized with minimum time delay, dynamic models that are trained online will be indispensable.…”

Section: F Quantization-aware Model Trainingmentioning

confidence: 99%

Self-Evolving Integrated Vertical Heterogeneous Networks

Farajzadeh¹,

Khoshkholgh²,

Yanıkömeroğlu³

et al. 2021

Preprint

View full text Add to dashboard Cite

The evolution of future networks into fully autonomous entities appears inevitable. The need for greater operational agility in supporting a wide range of services and use cases together with increasing network complexity creates, in all likelihood, unforeseen new challenges. 6G and beyond networks will have a disruptive architecture imposing some crucial requirements:1) Support universal access to intelligence sustained by a distributed computing, sensing, and control infrastructure; 2) manage with a unified framework of a heterogeneous communication, computing, caching, and control infrastructure; 3) support highly dynamic and possibly intermittent networks of vertical networks.This study first advocates the merits of integrated vertical heterogeneous network (VHetNet) architecture in support of 6G infrastructure. We then review the current literature on network management of vertical networks and discuss a unified network management framework to analyze new architecture-dependent challenges and their coordination with existing network management services and requirements. Third, we investigate recent advancements in artificial intelligence (AI)/machine learning (ML) methods in current VHetNets and discuss the core challenges of integrating AI/ML in VHetNets. Finally, we discuss potential future research directions for advancing the autonomous and evolving capabilities of VHetNets.

show abstract

Deep Learning Optimization for Edge Devices: Analysis of Training Quantization Parameters

Cited by 12 publications

References 16 publications

Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey

Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey

Self-Evolving Integrated Vertical Heterogeneous Networks

Self-Evolving Integrated Vertical Heterogeneous Networks

Contact Info

Product

Resources

About