TinyOL: TinyML with Online-Learning on Microcontrollers

Ren, Haoyu; Anicic, Darko; Runkler, Thomas A.

doi:10.1109/ijcnn52387.2021.9533927

Cited by 85 publications

(54 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ultra-low-power devices have been designed for always-on applications [7] [11]. Various algorithms have been proposed to fully exploit ML models on the devices without compromising performance [22] [17]. Collaborative ecosystems can further squeeze the potential from the synergism of hardware and software [5] [16].…”

Section: Related Workmentioning

confidence: 99%

“…Ontology We presented an ontology 15 [17] to describe NN models in the context of IoT, as shown in Figure 2. By reusing existing schemas, such as S3N and SOSA, we aligned the ontology with other Web standards and avoided reinventing the wheel.…”

Section: Semantic Systemmentioning

confidence: 99%

“…Semantic similarity search: Imagine if hundreds of thousands of IIoT devices and NN models were hosted in the KG, it would be tedious to examine them one after another manually. Semantic similarity search 17 enables users to explore relevant objects in the KG by typing a search text, similar to Google Search. In our example, users can search the stored components by filling in the provided form with their requirements, as shown in Figure 4.…”

Section: Low-code Platform Integrationmentioning

confidence: 99%

See 2 more Smart Citations

SeLoC-ML: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoT

Ren¹,

Dorofeev²,

Anicic³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Internet of Things (IoT) is transforming the industry by bridging the gap between Information Technology (IT) and Operational Technology (OT). Machines are being integrated with connected sensors and managed by intelligent analytics applications, accelerating digital transformation and business operations. Bringing Machine Learning (ML) to industrial devices is an advancement aiming to promote the convergence of IT and OT. However, developing an ML application in Industrial IoT (IIoT) presents various challenges, including hardware heterogeneity, non-standardized representations of ML models, device and ML model compatibility issues, and slow application development. Successful deployment in this area requires a deep understanding of hardware, algorithms, software tools, and applications. Therefore, this paper presents a framework called Semantic Low-Code Engineering for ML Applications (SeLoC-ML), built on a low-code platform to support the rapid development of ML applications in IIoT by leveraging Semantic Web technologies. SeLoC-ML enables non-experts to easily model, discover, reuse, and matchmake ML models and devices at scale. The project code can be automatically generated for deployment on hardware based on the matching results. Developers can benefit from semantic application templates, called recipes, to fast prototype end-user applications. The evaluations confirm an engineering effort reduction by a factor of at least three compared to traditional approaches on an industrial ML classification case study, showing the efficiency and usefulness of SeLoC-ML. We share the code and welcome any contributions 4 .

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Semantic Systemmentioning

confidence: 99%

Section: Low-code Platform Integrationmentioning

confidence: 99%

See 1 more Smart Citation

SeLoC-ML: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoT

Ren¹,

Dorofeev²,

Anicic³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, the TinyML paradigm arose, and research is being conducted on performing ML applications in the MCU efficiently. TinyML is a paradigm that focuses on compressing neural network models, rather than complex inputs or performance, to enable ML applications on MCU-based edge devices [7][8][9][10][11][12]. Furthermore, TinyML allows the conversion of a model trained in an ML framework and programmed in a high-level language like Python into a C/C++ program by separating it into an interpreter and weights.…”

Section: Related Workmentioning

confidence: 99%

Hardware/Software Co-Design for TinyML Voice-Recognition Application on Resource Frugal Edge Devices

Kwon

Park

2021

Applied Sciences

View full text Add to dashboard Cite

On-device artificial intelligence has attracted attention globally, and attempts to combine the internet of things and TinyML (machine learning) applications are increasing. Although most edge devices have limited resources, time and energy costs are important when running TinyML applications. In this paper, we propose a structure in which the part that preprocesses externally input data in the TinyML application is distributed to the hardware. These processes are performed using software in the microcontroller unit of an edge device. Furthermore, resistor–transistor logic, which perform not only windowing using the Hann function, but also acquire audio raw data, is added to the inter-integrated circuit sound module that collects audio data in the voice-recognition application. As a result of the experiment, the windowing function was excluded from the TinyML application of the embedded board. When the length of the hardware-implemented Hann window is 80 and the quantization degree is 2−5, the exclusion causes a decrease in the execution time of the front-end function and energy consumption by 8.06% and 3.27%, respectively.

show abstract

“…Therefore, a common direction of TinyML is to rethink the deployed Deep Neural Network (DNN) as a dynamic model that can adapt by learning from newly sensed data directly on the device. Recent progress in this research area concerns DNN model tuning, partial on-chip training [5] or unsupervised continual learning [6], which have been applied successfully to many IoT applications, such as anomaly detection tasks [7].…”

Section: Introductionmentioning

confidence: 99%

DARKSIDE: A Heterogeneous RISC-V Compute Cluster for Extreme-Edge On-Chip DNN Inference and Training

Garofalo

Tortorella

Perotti³

et al. 2022

IEEE Open J. Solid-State Circuits Soc.

View full text Add to dashboard Cite

On-chip DNN inference and training at the Extreme-Edge (TinyML) impose strict latency, throughput, accuracy and flexibility requirements. Heterogeneous clusters are promising solutions to meet the challenge, combining the flexibility of DSP-enhanced cores with the performance and energy boost of dedicated accelerators. We present DARKSIDE, a Systemon-Chip with a heterogeneous cluster of 8 RISC-V cores enhanced with 2-b to 32-b mixed-precision integer arithmetic. To boost performance and efficiency on key compute-intensive Deep Neural Network (DNN) kernels, the cluster is enriched with three digital accelerators: a specialized engine for low-data-reuse depthwise convolution kernels (up to 30 MAC/cycle); a minimal overhead datamover to marshal 1-b to 32-b data on-the-fly; a 16b floating point Tensor Product Engine (TPE) for tiled matrixmultiplication acceleration. DARKSIDE is implemented in 65nm CMOS technology. The cluster achieves a peak integer performance of 65 GOPS and a peak efficiency of 835 GOPS/W when working on 2-b integer DNN kernels. When targeting floatingpoint tensor operations, the TPE provides up to 18.2 GFLOPS of performance or 300 GFLOPS/W of efficiency -enough to enable on-chip floating-point training at competitive speed coupled with ultra-low power quantized inference.

show abstract

TinyOL: TinyML with Online-Learning on Microcontrollers

Cited by 85 publications

References 10 publications

SeLoC-ML: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoT

SeLoC-ML: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoT

Hardware/Software Co-Design for TinyML Voice-Recognition Application on Resource Frugal Edge Devices

DARKSIDE: A Heterogeneous RISC-V Compute Cluster for Extreme-Edge On-Chip DNN Inference and Training

Contact Info

Product

Resources

About