Implementation and Optimization of Neural Networks for Tiny Hardware Devices

Zein, Hadi Al; Aoude, Mohamad; Harkous, Youssef

doi:10.1109/ic2spm56638.2022.9988992

Cited by 3 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the proposed taxonomy in Figure 5, the area of model optimization, based on referenced research contributions, is the one that has received the most extensive exploration. Indeed, within TinyML, we come across several cutting-edge works that explore techniques such as pruning [63], quantization [75], and knowledge distillation [88]. On the contrary, the scarcity of research focusing on HPO [93] can be attributed to its complexity, the lack of awareness about the importance of HPO and its potential to enhance the performance of ML models significantly, and the resource requirements, which can be a limiting factor for researchers with restricted access to high-performance computing infrastructure.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Machine Learning-Oriented Survey on Tiny Machine Learning

Capogrosso,

Cunico,

Cheng

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The emergence of Tiny Machine Learning (TinyML) has positively revolutionized the field of Artificial Intelligence by promoting the joint design of resource-constrained IoT hardware devices and their learning-based software architectures. TinyML carries an essential role within the fourth and fifth industrial revolutions in helping societies, economies, and individuals employ effective AI-infused computing technologies (e.g., smart cities, automotive, and medical robotics). Given its multidisciplinary nature, the field of TinyML has been approached from many different angles: this comprehensive survey wishes to provide an up-to-date overview focused on all the learning algorithms within TinyML-based solutions. The survey is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodological flow, allowing for a systematic and complete literature survey. In particular, firstly, we will examine the three different workflows for implementing a TinyML-based system, i.e., MLoriented, HW-oriented, and co-design. Secondly, we propose a taxonomy that covers the learning panorama under the TinyML lens, examining in detail the different families of model optimization and design, as well as the state-of-the-art learning techniques. Thirdly, this survey will present the distinct features of hardware devices and software tools that represent the current state-of-the-art for TinyML intelligent edge applications. Finally, we discuss the challenges and future directions.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In general, knowledge distillation is used to achieve a good trade-off between a small model size and an acceptable accuracy [88]. For this reason, it is widely adopted in several fields where existing models are well-performing but unable to be deployed ''as they are'' in resource-constrained hardware.…”

Section: ) Knowledge Distillationmentioning

confidence: 99%

A Machine Learning-Oriented Survey on Tiny Machine Learning

Capogrosso,

Cunico,

Cheng

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

Quantization Effects of Deep Neural Networks on a FPGA platform

Pohl,

Vogel-Heuser,

Krüger

et al. 2024

2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS)

View full text Add to dashboard Cite

Optimizing Arduino Programming for IoT Devices Using Quantum and AI Techniques

V. G.,

Vagdevi,

Vindhya

et al. 2024

Advances in Computer and Electrical Engineering

View full text Add to dashboard Cite

The chapter discusses the utilization of advanced methodologies like Quantum Computing and AI in optimizing Arduino programming in IoT devices. The increasing popularity of IoT devices necessitates a growing need to enhance their performance and efficiency. It provides an in-depth explanation of the fundamental principles of Arduino programming and the challenges associated with IoT system programming.It then introduces Quantum Computing concepts, showing how quantum algorithms may resolve complex computational problems more efficiently than classical methods. In this respect, the chapter further goes into AI techniques, including machine learning and neural networks, to provide enhanced decision-making and prediction capabilities in IoT ecosystems. This chapter proposes a framework combining Quantum Computing and AI to optimize performance in IoT devices, demonstrating practical examples and combining them with Arduino-based systems.

show abstract

Implementation and Optimization of Neural Networks for Tiny Hardware Devices

Cited by 3 publications

References 29 publications

A Machine Learning-Oriented Survey on Tiny Machine Learning

A Machine Learning-Oriented Survey on Tiny Machine Learning

Quantization Effects of Deep Neural Networks on a FPGA platform

Optimizing Arduino Programming for IoT Devices Using Quantum and AI Techniques

Contact Info

Product

Resources

About