Making Neural Networks FAIR

Nguyen, Anna; Weller, Tobias; Färber, Michael; Sure-Vetter, York

doi:10.1007/978-3-030-65384-2_3

Cited by 6 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the efforts in hardware information modeling, very few [11] have addressed the modeling of the software stack, especially ML models, in the context of IoT. An existing ontology [32] describes NN models but lacks hardware-specific information. We have proposed a semantic ontology [42] tailored for NN models in IoT scenarios, with hardware specifications in mind, such as resource and platform requirements.…”

Section: Semantic Web Technology For Information Integrationmentioning

confidence: 99%

On-device Online Learning and Semantic Management of TinyML Systems

Ren,

Anicic,

et al. 2024

ACM Trans. Embed. Comput. Syst.

View full text Add to dashboard Cite

Recent advances in Tiny Machine Learning (TinyML) empower low-footprint embedded devices for real-time on-device Machine Learning (ML). While many acknowledge the potential benefits of TinyML, its practical implementation presents unique challenges. This study aims to bridge the gap between prototyping single TinyML models and developing reliable TinyML systems in production: (1) Embedded devices operate in dynamically changing conditions. Existing TinyML solutions primarily focus on inference, with models trained offline on powerful machines and deployed as static objects. However, static models may underperform in the real world due to evolving input data distributions. We propose online learning to enable training on constrained devices, adapting local models towards the latest field conditions. (2) Nevertheless, current on-device learning methods struggle with heterogeneous deployment conditions and the scarcity of labeled data when applied across numerous devices. We introduce federated meta-learning incorporating online learning to enhance model generalization, facilitating rapid learning. This approach ensures optimal performance among distributed devices by knowledge sharing. (3) Moreover, TinyML’s pivotal advantage is widespread adoption. Embedded devices and TinyML models prioritize extreme efficiency, leading to diverse characteristics ranging from memory and sensors to model architectures. Given their diversity and non-standardized representations, managing these resources becomes challenging as TinyML systems scale up. We present semantic management for the joint management of models and devices at scale. We demonstrate our methods through a basic regression example and then assess them in three real-world TinyML applications: handwritten character image classification, keyword audio classification, and smart building presence detection. The results confirm the effectiveness of our approaches from various perspectives, such as accuracy improvement, resource savings, and engineering effort reduction.

show abstract

Section: Semantic Web Technology For Information Integrationmentioning

confidence: 99%

On-device Online Learning and Semantic Management of TinyML Systems

Ren,

Anicic,

et al. 2024

ACM Trans. Embed. Comput. Syst.

View full text Add to dashboard Cite

show abstract

“…Similarly, authors in [31] described a database for tracking ML models. A KG called FAIRnets [17] collects information about publicly available neural networks and makes them exchangeable. Although all methods mentioned above provide certain degrees of expressiveness about ML models, they fall short in TinyML.…”

Section: Related Workmentioning

confidence: 99%

How to Manage Tiny Machine Learning at Scale: An Industrial Perspective

Ren¹,

Anicic²,

Runkler³

2022

Preprint

View full text Add to dashboard Cite

Tiny machine learning (TinyML) has gained widespread popularity where machine learning (ML) is democratized on ubiquitous microcontrollers, processing sensor data everywhere in real-time. To manage TinyML in the industry, where mass deployment happens, we consider the hardware and software constraints, ranging from available onboard sensors and memory size to ML-model architectures and runtime platforms. However, Internet of Things (IoT) devices are typically tailored to specific tasks and are subject to heterogeneity and limited resources. Moreover, TinyML models have been developed with different structures and are often distributed without a clear understanding of their working principles, leading to a fragmented ecosystem. Considering these challenges, we propose a framework using Semantic Web technologies to enable the joint management of TinyML models and IoT devices at scale, from modeling information to discovering possible combinations and benchmarking, and eventually facilitate TinyML component exchange and reuse. We present an ontology (semantic schema) for neural network models aligned with the World Wide Web Consortium (W3C) Thing Description, which semantically describes IoT devices. Furthermore, a Knowledge Graph of 23 publicly available ML models and six IoT devices were used to demonstrate our concept in three case studies, and we shared the code and examples to enhance reproducibility: Github

show abstract

“…In this work, we design the vocabulary for on-device applications based on S3N. There is also an ontology that describes neural network models [45]. However, this ontology (1) includes much unnecessary and redundant information relating to the optimizer, cost function, training dataset, and organization; (2) does not include information about the weights of the model, which renders its redeployment impossible; (3) is not suitable for the IoT environment, as it does not provide IoT/edge-speciic information, for example, memory requirements, and quantization; (4) is not designed for ONNX [19], an open exchange format proposed to bridge diferent ecosystems with a common representation of NN model, and to help reduce interoperability in future developments.…”

Section: Semantic Web Of Thingsmentioning

confidence: 99%

Towards Semantic Management of On-Device Applications in Industrial IoT

Ren

Anicic

Runkler

2022

ACM Trans. Internet Technol.

View full text Add to dashboard Cite

The Internet of Things (IoT) is revolutionizing the industry. Powered by pervasive embedded devices, the Industrial IoT (IIoT) provides a unique solution for retrieving and analyzing data near the source in real-time. Many emerging techniques, such as Tiny Machine Learning (TinyML) and Complex Event Processing (CEP), are actively being developed to support decision making at the edge, shifting the paradigm from centralized processing to distributed computing. However, distributed computing presents management challenges, as IoT devices are diverse and constrained, and their number is growing exponentially. The situation is even more challenging when various on-device applications (so-called artifacts) are deployed across decentralized IoT networks. Questions to be addressed include how to discover an appropriate function, whether that function can be executed on a certain device, and how to orchestrate a cross-platform service. To tackle these challenges, we propose an approach for the scalable management of on-device applications among distributed IoT devices. By leveraging the W3C Web of Things (WoT), the capabilities of each IoT device, or more precisely, its interaction patterns, can be semantically expressed in a Thing Description (TD). In addition, we introduce semantic modeling of on-device applications to supplement an TD with additional information regarding applications on the device. Specifically, we demonstrate two examples of semantic modeling: neural networks (NN) and CEP rules. The ontologies are evaluated by answering a set of competency questions. By hosting the enriched semantic knowledge of the entire IoT system in a Knowledge Graph (KG), we can discover and interoperate edge devices and artifacts across the decentralized network. This can reduce fragmentation and increase the reusability of IoT components. We demonstrate the feasibility of our concept on an industrial workstation consisting of a conveyor belt and several IoT devices. Finally, the requirements for constructing an IoT semantic management system are discussed.

show abstract

Making Neural Networks FAIR

Cited by 6 publications

References 19 publications

On-device Online Learning and Semantic Management of TinyML Systems

On-device Online Learning and Semantic Management of TinyML Systems

How to Manage Tiny Machine Learning at Scale: An Industrial Perspective

Towards Semantic Management of On-Device Applications in Industrial IoT

Contact Info

Product

Resources

About