# TinyML相關學術論文
這裡主要搜集單晶片（MCU）等級的機器學習、人工智慧、深度學習等相關研究及論文。而單板微電腦(SBC)、行動裝置或小型工業電腦等級之相關研究及論文請參考另一篇「[Edge AI相關學術論文](https://hackmd.io/@OmniXRI-Jack/EdgeAI_papers)」。

註：相關論文連結不一定有提供PDF可供下載，或者必須有學術網路帳號才能下載，請自行點擊查閱。以下論文清單依發表時間(相同月份）由新到舊月份排序。目前小計496篇。

最後更新日期 : 2023/11/29
上一次更新日期 : 2022/10/20

## 2023(102)

### Dec. 2023(1)
* [On the adversarial robustness of full integer quantized TinyML models at the edge](https://dl.acm.org/doi/10.1145/3630180.3631201)

### Nov. 2023(20)
* [Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review](https://arxiv.org/abs/2311.11883)
* [Double-Condensing Attention Condenser: Leveraging Attention in Deep Learning to Detect Skin Cancer from Skin Lesion Images](https://arxiv.org/abs/2311.11656)
* [Physics-Enhanced TinyML for Real-Time Detection of Ground Magnetic Anomalies](https://arxiv.org/abs/2311.11452)
* [Energy-efficient Wireless Image Retrieval for IoT Devices by Transmitting a TinyML Model](https://arxiv.org/abs/2311.04788)
* [TinyFormer: Efficient Transformer Design and Deployment on Tiny Devices](https://arxiv.org/abs/2311.01759)
* [Smart Buildings: Water Leakage Detection Using TinyML](https://www.mdpi.com/1424-8220/23/22/9210)
* [Enabling Efficient Intermittent Computing on Brand New Microcontrollers via Tracking Programmable Voltage Thresholds](https://dl.acm.org/doi/10.1145/3628353.3628547)
* [Tiny machine learning on the edge: A framework for transfer learning empowered unmanned aerial vehicle assisted smart farming](https://ietresearch.onlinelibrary.wiley.com/doi/full/10.1049/smc2.12072)
* [Object Detection at Edge Using TinyML Models](https://link.springer.com/article/10.1007/s42979-023-02304-z)
* [An IoT Based New Platform for Teaching Tiny Machine Learning](https://iscap.us/proceedings/2023/pdf/5973.pdf)
* [Machine Learning Hardware Implementation of Handwritten Digit Inference using Arduino and Ternary Output Binary Neural Network](https://ieeexplore.ieee.org/document/10326336)
* [Development of an electrocardiographic signal classifier for bundle branch blocks, applying Tiny Machine Learning](https://ieeexplore.ieee.org/document/10326046)
* [Advanced IoT-Based Fire and Smoke Detection System leveraging Deep Learning and TinyML](https://ieeexplore.ieee.org/document/10307805)
* [Work-in-Progress: Micro-Accelerator-in-the-Loop Framework for MCU Integrated Accelerator Peripheral Fast Prototyping](https://ieeexplore.ieee.org/document/10316390)
* [V-CNN: A Versatile Light CNN Structure For Image Recognition On Resources Constrained Platforms](https://ieeexplore.ieee.org/document/10310339)
* [Enabling ImageNet-Scale Deep Learning on MCUs for Accurate and Efficient Inference](https://eprints.soton.ac.uk/483972/)
* [A Comprehensive Android App Based Solution for Automated Attendance and Management in Institutions Using IoT and TinyML](https://ieeexplore.ieee.org/document/10303506)
* [Combining Multiple tinyML Models for Multimodal Context-Aware Stress Recognition on Constrained Microcontrollers](https://ieeexplore.ieee.org/document/10305501)
* [A review of on-device machine learning for IoT: An energy perspective](https://www.sciencedirect.com/science/article/abs/pii/S1570870523002688)
* [ColabNAS: Obtaining lightweight task-specific convolutional neural networks following Occam’s razor](https://www.sciencedirect.com/science/article/pii/S0167739X23004028)

### Oct. 2023(14)
* [Optimizing IoT-Based Asset and Utilization Tracking: Efficient Activity Classification with MiniRocket on Resource-Constrained Devices](https://arxiv.org/abs/2310.14758)
* [Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices](https://arxiv.org/abs/2310.07217)
* [Unsupervised deep learning framework for temperature-compensated damage assessment using ultrasonic guided waves on edge device](https://arxiv.org/abs/2310.05154)
* [Quantized Transformer Language Model Implementations on Edge Devices](https://arxiv.org/abs/2310.03971)
* [Study of the Complexity of CMOS Neural Network Implementations Featuring Heart Rate Detection](https://www.mdpi.com/2079-9292/12/20/4291)
* [ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks](https://dl.acm.org/doi/10.1145/3629522)
* [Posture Guardian With Smart Muscle Strain Detection And Correction Using TINYML](https://propulsiontechjournal.com/index.php/journal/article/view/1873)
* [TinyMM: Multimodal-Multitask Machine Learning on Low-Power MCUs for Smart Glasses](https://ieeexplore.ieee.org/document/10325296)
* [Enhancing Lightweight Neural Networks for Small Object Detection in IoT Applications](https://ieeexplore.ieee.org/document/10325126)
* [AutoML for On-Sensor Tiny Machine Learning](https://ieeexplore.ieee.org/document/10298625)
* [Industrial Visual Inspection with TinyML for High-Performance Quality Control](https://ieeexplore.ieee.org/document/10292593)
* [Tiny Machine Learning: Progress and Futures](https://ieeexplore.ieee.org/document/10284551)
* [Event-Driven Edge Deep Learning Decoder for Real-Time Gesture Classification and Neuro-Inspired Rehabilitation Device Control](https://ieeexplore.ieee.org/document/10285603)
* [Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices](https://ieeexplore.ieee.org/document/10278089)

### Sep. 2023(5)
* [A Machine Learning-oriented Survey on Tiny Machine Learning](https://arxiv.org/abs/2309.11932)
* [AoCStream: All-on-Chip CNN Accelerator with Stream-Based Line-Buffer Architecture and Accelerator-Aware Pruning](https://www.mdpi.com/1424-8220/23/19/8104)
* [Design and Implementation of an Internet-of-Things-Enabled Smart Meter and Smart Plug for Home-Energy-Management System](https://www.mdpi.com/2079-9292/12/19/4041)
* [Synergy of Patent and Open-Source-Driven Sustainable Climate Governance under Green AI: A Case Study of TinyML](https://www.mdpi.com/2071-1050/15/18/13779)
* [Low-cost air, noise, and light pollution measuring station with wireless communication and tinyML](https://www.sciencedirect.com/science/article/pii/S2468067223000846)

### Aug. 2023(6)
* [TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning](https://arxiv.org/abs/2308.09201)
* [MRQ:Support Multiple Quantization Schemes through Model Re-Quantization](https://arxiv.org/abs/2308.01867)
* [first_pagesettingsOrder Article Reprints Open AccessArticle An Efficient, Lightweight, Tiny 2D-CNN Ensemble Model to Detect Cardiomegaly in Heart CT Images](https://www.mdpi.com/2075-4426/13/9/1338)
* [Machine-Learning-Based Spectroscopic Technique for Non-Destructive Estimation of Shelf Life and Quality of Fresh Fruits Packaged under Modified Atmospheres](https://www.mdpi.com/2071-1050/15/17/12871)
* [Gait Stride Length Estimation Using Embedded Machine Learning](https://www.mdpi.com/1424-8220/23/16/7166)
* [TinyML-Sensor for Shelf Life Estimation of Fresh Date Fruits](https://www.mdpi.com/1424-8220/23/16/7081)

### Jul. 2023(2)
* [TinyMetaFed: Efficient Federated Meta-Learning for TinyML](https://arxiv.org/abs/2307.06822)
* [The Design and Optimization of an Acoustic and Ambient Sensing AIoT Platform for Agricultural Applications](https://www.mdpi.com/1424-8220/23/14/6262)

### Jun. 2023（6）
* [U-TOE: Universal TinyML On-board Evaluation Toolkit for Low-Power IoT](https://arxiv.org/abs/2306.14574)
* [MLonMCU: TinyML Benchmarking with Fast Retargeting](https://arxiv.org/abs/2306.08951)
* [RAMAN: A Re-configurable and Sparse tinyML Accelerator for Inference on Edge](https://arxiv.org/abs/2306.06493)
* [TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers](https://arxiv.org/abs/2306.00001)
* [DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning](https://www.mdpi.com/1424-8220/23/12/5696)
* [Scalable Lightweight IoT-Based Smart Weather Measurement System](https://www.mdpi.com/1424-8220/23/12/5569)

### May 2023(8)
* [Reduced Precision Floating-Point Optimization for Deep Neural Network On-Device Learning on MicroControllers](https://arxiv.org/abs/2305.19167)
* [AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computing](https://arxiv.org/abs/2305.10459)
* [TinyML Design Contest for Life-Threatening Ventricular Arrhythmia Detection](https://arxiv.org/abs/2305.05105)
* [Cheshire: A Lightweight, Linux-Capable RISC-V Host Platform for Domain-Specific Accelerator Plug-In](https://arxiv.org/abs/2305.04760)
* [TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers](https://arxiv.org/abs/2306.00001)
* [Trends and Challenges in AIoT/IIoT/IoT Implementation](https://www.mdpi.com/1424-8220/23/11/5074)
* [Persistence Landscapes—Implementing a Dataset Verification Method in Resource-Scarce Embedded Systems](https://www.mdpi.com/2073-431X/12/6/110)
* [TinyM2Net-V2: A Compact Low Power Software Hardware Architecture for Multimodal Deep Neural Networks](https://dl.acm.org/doi/10.1145/3595633)

### Apl. 2023(13)
* [Multiplierless In-filter Computing for tinyML Platforms](https://arxiv.org/abs/2304.11816)
* [The Case for Hierarchical Deep Learning Inference at the Network Edge](https://arxiv.org/abs/2304.11763)
* [Device management and network connectivity as missing elements in TinyML landscape](https://arxiv.org/abs/2304.11669)
* [SSS3D: Fast Neural Architecture Search For Efficient Three-Dimensional Semantic Segmentation](https://arxiv.org/abs/2304.11207)
* [Cashew dataset generation using augmentation and RaLSGAN and a transfer learning based tinyML approach towards disease detection](https://arxiv.org/abs/2304.08766)
* [How Tiny Can Analog Filterbank Features Be Made for Ultra-low-power On-device Keyword Spotting?](https://arxiv.org/abs/2304.08541)
* [MEMA Runtime Framework: Minimizing External Memory Accesses for TinyML on Microcontrollers](https://arxiv.org/abs/2304.05544)
* [TinyReptile: TinyML with Federated Meta-Learning](https://arxiv.org/abs/2304.05201)
* [SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers](https://arxiv.org/abs/2304.03986)
* [Data Aware Neural Architecture Search](https://arxiv.org/abs/2304.01821)
* [A Super-Efficient TinyML Processor for the Edge Metaverse](https://www.mdpi.com/2078-2489/14/4/235)
* [DNN Is Not All You Need: Parallelizing Non-neural ML Algorithms on Ultra-low-power IoT Processors](https://dl.acm.org/doi/10.1145/3571133)
* [Constrained Tiny Machine Learning for Predicting Gas Concentration with I4.0 Low-cost Sensors](https://dl.acm.org/doi/10.1145/3590956)

### Mar. 2023(6)
* [DARKSIDE: A Heterogeneous RISC-V Compute Cluster for Extreme-Edge On-Chip DNN Inference and Training](https://arxiv.org/abs/2303.17954)
* [Fused Depthwise Tiling for Memory Optimization in TinyML Deep Neural Network Inference](https://arxiv.org/abs/2303.17878)
* [FMAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation](https://arxiv.org/abs/2303.16322)
* [TinyML: Tools, Applications, Challenges, and Future Research Directions](https://arxiv.org/abs/2303.13569)
* [Convolutional Neural Network-Based Low-Powered Wearable Smart Device for Gait Abnormality Detection](https://www.mdpi.com/2624-831X/4/2/4)
* [A Gas Leakage Detection Device Based on the Technology of TinyML](https://www.mdpi.com/2227-7080/11/2/45)

### Feb. 2023(7)
* [MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption](https://arxiv.org/abs/2302.12347)
* [LimitAccess: on-device TinyML based robust speech recognition and age classification](https://link.springer.com/article/10.1007/s44163-023-00051-x)
* [An evaluation methodology to determine the actual limitations of a TinyML-based solution](https://www.sciencedirect.com/science/article/abs/pii/S2542660523000525)
* [Coding Mel Spectrogram using Keras and Tensorflow for Home Appliances Tiny Classification](https://ieeexplore.ieee.org/abstract/document/10043378)
* [Evaluation of low-power devices for smart greenhouse development](https://link.springer.com/article/10.1007/s11227-023-05076-8)
* [An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments](https://www.mdpi.com/1424-8220/23/4/2344)
* [Selective Sensing of Mixtures of Gases with CMOS-SOI-MEMS Sensor Dubbed GMOS](https://www.mdpi.com/2072-666X/14/2/390)

### Jan. 2023(14)
* [Editorial for the Special Issue on Micro and Smart Devices and Systems](https://www.mdpi.com/2072-666X/14/1/164)
* [An Impact Localization Solution Using Embedded Intelligence—Methodology and Experimental Verification via a Resource-Constrained IoT Device](https://www.mdpi.com/1424-8220/23/2/896)
* [Intelligent and Efficient IoT Through the Cooperation of TinyML and Edge Computing](https://www.informatica.vu.lt/journal/INFORMATICA/article/1281/text)
* [Developing a TinyML-Oriented Deep Learning Model for an Intelligent Greenhouse Microclimate Control from Multivariate Sensed Data](https://link.springer.com/chapter/10.1007/978-981-19-7663-6_27)
* [An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments](https://www.mdpi.com/1424-8220/23/4/2344)
* [A TinyML Deep Learning Approach for Indoor Tracking of Assets](https://www.mdpi.com/1424-8220/23/3/1542)
* [Lightweight and Energy-Efficient Deep Learning Accelerator for Real-Time Object Detection on Edge Devices](https://www.mdpi.com/1424-8220/23/3/1185)
* [BandX : An Intelligent IoT-band for Human Activity Recognition based on TinyML](https://dl.acm.org/doi/abs/10.1145/3571306.3571415)
* [Employing Machine Learning and IoT for Earthquake Early Warning System in Smart Cities](https://www.mdpi.com/1996-1073/16/1/495)
* [On the Adoption of Modern Technologies to Fight the COVID-19 Pandemic: A Technical Synthesis of Latest Developments](https://www.mdpi.com/2673-8112/3/1/6)
* [An Impact Localization Solution Using Embedded Intelligence—Methodology and Experimental Verification via a Resource-Constrained IoT Device](https://www.mdpi.com/1424-8220/23/2/896)
* [RedMule: A Mixed-Precision Matrix-Matrix Operation Engine for Flexible and Energy-Efficient On-Chip Linear Algebra and TinyML Training Acceleration](https://arxiv.org/abs/2301.03904)
* [Empirical study of the modulus as activation function in computer vision applications](https://arxiv.org/abs/2301.05993)
* [Is TinyML Sustainable? Assessing the Environmental Impacts of Machine Learning on Microcontrollers](https://arxiv.org/abs/2301.11899)
* [Weightless Neural Networks for Efficient Edge Inference](https://dl.acm.org/doi/10.1145/3559009.3569680)

## 2022(183)

### Dec. 2022(12)
* [Energy consumption of on-device machine learning models for IoT intrusion detection](https://www.sciencedirect.com/science/article/pii/S2542660522001512)
* [Applying Azure To Automate Dev Ops For Small ML Smart Sensors](https://www.irjmets.com/uploadedfiles/paper/issue_12_december_2022/32238/final/fin_irjmets1671423099.pdf)
* [Edge Impulse: An MLOps Platform for Tiny Machine Learning](https://arxiv.org/abs/2212.03332)
* [TCN-CUTIE: A 1036 TOp/s/W, 2.72 uJ/Inference, 12.2 mW All-Digital Ternary Accelerator in 22 nm FDX Technology](https://arxiv.org/abs/2212.00688)
* [Neuromorphic Computing and Sensing in Space](https://arxiv.org/abs/2212.05236)
* [Rethinking Vision Transformers for MobileNet Size and Speed](https://arxiv.org/abs/2212.08059)
* [In-Sensor & Neuromorphic Computing are all you need for Energy Efficient Computer Vision](https://arxiv.org/abs/2212.10881)
* [Edge Impulse: An MLOps Platform for Tiny Machine Learning](https://arxiv.org/abs/2212.03332)
* [Towards Energy-Aware Tinyml on Battery-Less Iot Devices](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4300436)
* [TinyML for Ultra-Low Power AI and Large Scale IoT Deployments: A Systematic Review](https://www.mdpi.com/1999-5903/14/12/363)
* [Tiny Machine Learning for High Accuracy Product Quality Inspection](https://ieeexplore.ieee.org/abstract/document/9969601)
* [Book: Machine Learning on Commodity Tiny Devices](https://www.taylorfrancis.com/books/edit/10.1201/9781003340225/machine-learning-commodity-tiny-devices-song-guo-qihua-zhou)

### Nov. 2022(4)
* [An embedded solution for fault detection and diagnosis of photovoltaic modules using thermographic images and deep convolutional neural networks](https://www.sciencedirect.com/science/article/abs/pii/S0952197622004493)
* [AutoTinyML for microcontrollers: Dealing with black-box deployability](https://www.sciencedirect.com/science/article/abs/pii/S0957417422011289)
* [A review of TinyML](https://arxiv.org/abs/2211.04448)
* [PreMa: Predictive Maintenance of Solenoid Valve in Real-Time at Embedded Edge-Level](https://arxiv.org/abs/2211.12326)

### Oct. 2022(21)
* [TinyML-enabled edge implementation of transfer learning framework for domain generalization in machine fault diagnosis](https://www.sciencedirect.com/science/article/abs/pii/S0957417422020346)
* [Feasibility on Detecting Door Slamming towards Monitoring Early Signs of Domestic Violence](https://arxiv.org/abs/2210.02642)
* [Optimizing Random Forest Based Inference on RISC-V MCUs at the Extreme Edge](https://ieeexplore.ieee.org/document/9925686)
* [Optimizing PhiNet architectures for the detection of urban sounds on low-end devices](https://ieeexplore.ieee.org/document/9909572)
* [Accurate Estimation of the CNN Inference Cost for TinyML Devices](https://ieeexplore.ieee.org/document/9908108)
* [Machine Learning for Microcontroller-Class Hardware - A Review](https://ieeexplore.ieee.org/document/9912325)
* [TinyML-Enabled Static Hand Gesture Recognition System Based on an Ultra-Low Resolution Infrared Array Sensor and a Low-Cost AI Chip](https://ieeexplore.ieee.org/document/9904109)
* [DeepPicarMicro: Applying TinyML to Autonomous Cyber Physical Systems](https://ieeexplore.ieee.org/document/9904754)
* [TMM-TinyML: tensor memory mapping (TMM) method for tiny machine learning (TinyML)](https://dl.acm.org/doi/10.1145/3495243.3558265)
* [TinyML-CAM: 80 FPS image recognition in 1 kB RAM](https://dl.acm.org/doi/10.1145/3495243.3558264)
* [PROS: an efficient pattern-driven compressive sensing framework for low-power biopotential-based wearables with on-chip intelligence](https://dl.acm.org/doi/10.1145/3495243.3560533)
* [TinyRL: Towards Reinforcement Learning on Tiny Embedded Devices](https://dl.acm.org/doi/10.1145/3511808.3557206)
* [Driving an innovation contest into crisis](https://dl.acm.org/doi/10.1145/3554917)
* [Guidelines for Artifacts to Support Industry-Relevant Research on Self-Adaptation](https://dl.acm.org/doi/10.1145/3561846.3561852)
* [Real-time neural network inference on extremely weak devices: agile offloading with explainable AI](https://dl.acm.org/doi/10.1145/3495243.3560551)
* [TinyML Gamma Radiation Classifier](https://www.sciencedirect.com/science/article/pii/S1738573322004648)
* [A novel framework for deployment of CNN models using post-training quantization on microcontroller](https://www.sciencedirect.com/science/article/abs/pii/S0141933122001715)
* [An embedded solution for fault detection and diagnosis of photovoltaic modules using thermographic images and deep convolutional neural networks](https://www.sciencedirect.com/science/article/abs/pii/S0952197622004493)
* [MinUn: Accurate ML Inference on Microcontrollers](https://arxiv.org/abs/2210.16556)
* [Split Federated Learning on Micro-controllers: A Keyword Spotting Showcase](https://arxiv.org/abs/2210.01961)
* [Enabling ISP-less Low-Power Computer Vision](https://arxiv.org/abs/2210.05451)

### Sep. 2022(21)
* [Is Tiny Deep Learning the New Deep Learning?](https://link.springer.com/chapter/10.1007/978-981-19-3391-2_2)
* [Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors](https://arxiv.org/abs/2209.00591)
* [TinyML for UWB-radar based presence detection](https://ieeexplore.ieee.org/document/9892925)
* [Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors](https://ieeexplore.ieee.org/document/9892356)
* [Darkside: A Heterogeneous RISC-V Compute Cluster for Extreme-Edge On-Chip DNN Inference and Training](https://ieeexplore.ieee.org/document/9903915)
* [WiFi Sensing on the Edge: Signal Processing Techniques and Challenges for Real-World Systems](https://ieeexplore.ieee.org/document/9900419)
* [Unlocking Edge Intelligence Through Tiny Machine Learning (TinyML)](https://ieeexplore.ieee.org/document/9893787)
* [An Intelligent IoT Sensing System for Rail Vehicle Running States Based on TinyML](https://ieeexplore.ieee.org/document/9893139)
* [Embedded Machine Learning Using Microcontrollers in Wearable and Ambulatory Systems for Health and Care Applications: A Review](https://ieeexplore.ieee.org/document/9893137)
* [Modelling Virtual Sensors for Indoor Environments with Machine Learning](https://ieeexplore.ieee.org/document/9881529)
* [tinyCare: A tinyML-based Low-Cost Continuous Blood Pressure Estimation on the Extreme Edge](https://ieeexplore.ieee.org/document/9874599)
* [Quantized ID-CNN for a Low-power PDM-to-PCM Conversion in TinyML KWS Applications](https://ieeexplore.ieee.org/document/9869909)
* [Real-Time Low Power Audio Distortion Circuit Modeling: a TinyML Deep Learning Approach](https://ieeexplore.ieee.org/document/9870024)
* [Survey and Comparison of Milliwatts Micro controllers for Tiny Machine Learning at the Edge](https://ieeexplore.ieee.org/document/9870017)
* [Tiny TCN model for Gesture Recognition With Multi-point Low power ToF-Sensors](https://ieeexplore.ieee.org/document/9869848)
* [Real-time Prediction Method of Remaining Useful Life Based on TinyML](https://ieeexplore.ieee.org/document/9872225)
* [Classifying mosquito wingbeat sound using TinyML](https://dl.acm.org/doi/10.1145/3524458.3547258)
* [Spotting the Elusive Grandis impactus in the HCI Savannah](https://dl.acm.org/doi/10.1145/3528575.3551453)
* [A Tiny CNN for Embedded Electronic Skin Systems](https://link.springer.com/chapter/10.1007/978-3-031-16281-7_53)
* [Free Bits: Platform-Aware Latency Optimization of Mixed-Precision Neural Networks for Edge Deployment](https://openreview.net/forum?id=_GcWoi0SQm)
* [FP8 Formats for Deep Learning](https://arxiv.org/abs/2209.05433)
* [A low-cost TinyML model for Mosquito Detection in Resource-Constrained Environments](https://dl.acm.org/doi/abs/10.1145/3582515.3609514)

### Aug. 2022(19)
* [DeepPicarMicro: Applying TinyML to Autonomous Cyber Physical Systems](https://arxiv.org/abs/2208.11212)
* [Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture for the Edge via Double-Condensing Attention Condensers](https://arxiv.org/abs/2208.06980)
* [TinyML Model for Classifying Hazardous Volatile Organic Compounds Using Low-Power Embedded Edge Sensors: Perfecting Factory 5.0 Using Edge AI](https://ieeexplore.ieee.org/document/9866105)
* [TinyOps: ImageNet Scale Deep Learning on Microcontrollers](https://ieeexplore.ieee.org/document/9857160)
* [A TinyML Soft-Sensor for the Internet of Intelligent Vehicles](https://ieeexplore.ieee.org/document/9855110)
* [ML Blocks: A Block-Based, Graphical User Interface for Creating TinyML Models](https://ieeexplore.ieee.org/document/9833149)
* [Assurance of Machine Learning/TinyML in Safety-Critical Domains](https://ieeexplore.ieee.org/document/9833112)
* [ML-HW Co-Design of Noise-Robust TinyML Models and Always-On Analog Compute-in-Memory Edge Accelerator](https://ieeexplore.ieee.org/document/9855854)
* [Supporting AI Engineering on the IoT Edge through Model-Driven TinyML](https://ieeexplore.ieee.org/document/9842593)
* [Automated Neural and On-Device Learning for Micro Controllers](https://ieeexplore.ieee.org/document/9843050)
* [Neural Network Decomposition and Distribution on Multiple Microcontrollers](https://ieeexplore.ieee.org/document/9843133)
* [TinyMLOps: Operational Challenges for Widespread Edge AI Adoption](https://ieeexplore.ieee.org/document/9835378)
* [A Guided Task and Obstacle Alert Robot System Based on TinyML and Augmented Reality](https://dl.acm.org/doi/10.1145/3562007.3562050)
* [Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks](https://dl.acm.org/doi/10.1145/3531437.3539720)
* [An instance-based deep transfer learning approach for resource-constrained environments](https://dl.acm.org/doi/10.1145/3538393.3544938)
* [Reducing Energy Consumption and Health Hazards of Electric Liquid Mosquito Repellents through TinyML](https://www.mdpi.com/1424-8220/22/17/6421)
* [Developing a multi-label tinyML machine learning model for an active and optimized greenhouse microclimate control from multivariate sensed data](https://www.sciencedirect.com/science/article/pii/S2589721722000101)
* [PULP-TrainLib: Enabling On-Device Training for RISC-V Multi-core MCUs Through Performance-Driven Autotuning](https://openreview.net/forum?id=-4AlFLBP353)
* [TinyRCE: Multipurpose Forward Learning for Resource Restricted Devices](https://ieeexplore.ieee.org/abstract/document/10225676)

### Jul. 2022(22)
* [Implementation Of Tiny Machine Learning Models On Arduino 33 BLE For Gesture And Speech Recognition](https://arxiv.org/abs/2207.12866)
* [T-RECX: Tiny-Resource Efficient Convolutional Neural Networks with Early-Exit](https://arxiv.org/abs/2207.06613)
* [An Ultra-low Power TinyML System for Real-time Visual Processing at Edge](https://arxiv.org/abs/2207.04663)
* [A TinyML-based system for gas leakage detection](https://ieeexplore.ieee.org/document/9837510)
* [A data-stream TinyML compression algorithm for vehicular applications: a case study](https://ieeexplore.ieee.org/document/9831606)
* [A TinyML approach to non-repudiable anomaly detection in extreme industrial environments](https://ieeexplore.ieee.org/document/9831517)
* [TinyML Smart Sensor for Energy Saving in Internet of Things Precision Agriculture platform](https://ieeexplore.ieee.org/document/9829675)
* [Software Engineering Approaches for TinyML based IoT Embedded Vision: A Systematic Literature Review](https://ieeexplore.ieee.org/document/9826176)
* [Poster Abstract: Approach for Remote, On-Demand loading and Execution of TensorFlow Lite ML Models on Arduino IoT Boards](https://ieeexplore.ieee.org/document/9825918)
* [Poster Abstract: Embedded ML Pipeline for Precision Agriculture](https://ieeexplore.ieee.org/document/9825977)
* [iBUG: AI Enabled IoT Sensing Platform for Real-time Environmental Monitoring](https://ieeexplore.ieee.org/document/9826935)
* [Recent Advances in Plant Diseases Detection With Machine Learning: Solution for Developing Countries](https://ieeexplore.ieee.org/document/9821066)
* [The C-CNN model: Do we really need multiplicative synapses in convolutional neural networks?](https://ieeexplore.ieee.org/document/9817267)
* [Custom Hardware Inference Accelerator for TensorFlow Lite for Microcontrollers](https://ieeexplore.ieee.org/document/9825651)
* [FlashMAC: A Time-Frequency Hybrid MAC Architecture With Variable Latency-Aware Scheduling for TinyML Systems](https://ieeexplore.ieee.org/document/9813564)
* [Towards on-board learning for harvested energy prediction](https://dl.acm.org/doi/10.1145/3539491.3539593)
* [Monitoring neurological disorders with AI-enabled wearable systems](https://dl.acm.org/doi/10.1145/3539494.3542755)
* [TinyOdom: Hardware-Aware Efficient Neural Inertial Navigation](https://dl.acm.org/doi/10.1145/3534594)
* [A Practical View on Training Neural Networks in the Edge](https://www.sciencedirect.com/science/article/pii/S2405896322003603)
* [ACTION: Automated Hardware-Software Codesign Framework for Low-precision Numerical Format SelecTION in TinyML](https://link.springer.com/chapter/10.1007/978-3-031-09779-9_4)
* [Real Time Classification of Fruits and Vegetables Deployed on Low Power Embedded Devices Using Tiny ML](https://link.springer.com/chapter/10.1007/978-3-031-12413-6_27)
* [Elements of TinyML on Constrained Resource Hardware](https://link.springer.com/chapter/10.1007/978-3-031-12641-3_26)

### Jun. 2022(12)
* [On-Device Training Under 256KB Memory](https://arxiv.org/abs/2206.15472)
* [OTA-TinyML: Over the Air Deployment of TinyML Models and Execution on IoT Devices](https://ieeexplore.ieee.org/document/9811289)
* [YOLO-Based Face Mask Detection on Low-End Devices Using Pruning and Quantization](https://ieeexplore.ieee.org/document/9803406)
* [Optimizations of Ternary Generative Adversarial Networks](https://ieeexplore.ieee.org/document/9797400)
* [RIS-IoT: Towards Resilient, Interoperable, Scalable IoT](https://ieeexplore.ieee.org/document/9797511)
* [Poster Abstract: Feasibility on Detecting Door Slamming towards Monitoring Early Signs of Domestic Violence](https://ieeexplore.ieee.org/document/9797406)
* [Comparison of Two Microcontroller Boards for On-Device Model Training in a Keyword Spotting Task](https://ieeexplore.ieee.org/document/9797171)
* [Cough Detection System using TinyML](https://ieeexplore.ieee.org/document/9793426)
* [A Real-Time CNN-Based Lightweight Mobile Masked Face Recognition System](https://ieeexplore.ieee.org/document/9795021)
* [Google Home, Listen: Building Helper Intelligences for Non-Verbal Sound](https://dl.acm.org/doi/10.1145/3527927.3535202)
* [A Primer for tinyML Predictive Maintenance: Input and Model Optimisation](https://link.springer.com/chapter/10.1007/978-3-031-08337-2_6)
* [EtinyNet: Extremely Tiny Network for TinyML](https://ojs.aaai.org/index.php/AAAI/article/view/20387)

### May 2022(12)
* [Green Accelerated Hoeffding Tree](https://arxiv.org/abs/2205.03184)
* [A 1036 TOp/s/W, 12.2 mW, 2.72 μJ/Inference All Digital TNN Accelerator in 22 nm FDX Technology for TinyML Applications](https://ieeexplore.ieee.org/document/9772668)
* [Edge AI Based Autonomous UAV for Emergency Network Deployment: A Study Towards Search and Rescue Missions](https://ieeexplore.ieee.org/document/9767139)
* [TinyFedTL: Federated Transfer Learning on Ubiquitous Tiny IoT Devices](https://ieeexplore.ieee.org/document/9767250)
* [Noise Cleaning of ECG on Edge Device Using Convolutional Sparse Contractive Autoencoder](https://ieeexplore.ieee.org/document/9767313)
* [On the Role of Smart Vision Sensors in Energy-Efficient Computer Vision at the Edge](https://ieeexplore.ieee.org/document/9767380)
* [Online Stream Sampling for Low-Memory On-Device Edge Training for WiFi Sensing](https://dl.acm.org/doi/10.1145/3522783.3529521)
* [TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications](https://www.mdpi.com/2072-666X/13/6/851)
* [A TinyML Soft-Sensor Approach for Low-Cost Detection and Monitoring of Vehicular Emissions](https://www.mdpi.com/1424-8220/22/10/3838)
* [0-Dimensional Persistent Homology Analysis Implementation in Resource-Scarce Embedded Systems](https://www.mdpi.com/1424-8220/22/10/3657)
* [Utilization of mobile edge computing on the Internet of Medical Things: A survey](https://www.sciencedirect.com/science/article/pii/S2405959522000753)
* [Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation](https://arxiv.org/abs/2205.01271)

### Apr. 2022(13)
* [A review on TinyML: State-of-the-art and prospects](https://www.sciencedirect.com/science/article/pii/S1319157821003335)
* [Depth Pruning with Auxiliary Networks for TinyML](https://arxiv.org/abs/2204.10546)
* [Software Engineering Approaches for TinyML based IoT Embedded Vision: A Systematic Literature Review](https://arxiv.org/abs/2204.08702)
* [Intelligence at the Extreme Edge: A Survey on Reformable TinyML](https://arxiv.org/abs/2204.00827)
* [A Heterogeneous In-Memory Computing Cluster for Flexible End-to-End Inference of Real-World Deep Neural Networks](https://ieeexplore.ieee.org/document/9764758)
* [Depth Pruning with Auxiliary Networks for Tinyml](https://ieeexplore.ieee.org/document/9746843)
* [Scalable Neural Architectures for End-to-End Environmental Sound Classification](https://ieeexplore.ieee.org/document/9746093)
* [A Fall Detection using Sound Technology Based on TinyML](https://ieeexplore.ieee.org/document/9750658)
* [Design and Performance Evaluation of an Ultralow-Power Smart IoT Device With Embedded TinyML for Asset Activity Monitoring](https://ieeexplore.ieee.org/document/9758676)
* [Enabling Hyperparameter Tuning of Machine Learning Classifiers in Production](https://ieeexplore.ieee.org/document/9750322)
* [Digital twins and artificial intelligence: as pillars of personalized learning models](https://dl.acm.org/doi/10.1145/3478281)
* [Planetary digital twin: a case study in aquaculture](https://dl.acm.org/doi/10.1145/3477314.3508384)
* [Enhancing Food Supply Chain Security through the Use of Blockchain and TinyML](https://www.mdpi.com/2078-2489/13/5/213)

### Mar. 2022(19)
* [A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators](https://arxiv.org/abs/2203.13921)
* [TinyMLOps: Operational Challenges for Widespread Edge AI Adoption](https://arxiv.org/abs/2203.10923)
* [Distributed On-Sensor Compute System for AR/VR Devices: A Semi-Analytical Simulation Framework for Power Estimation](https://arxiv.org/abs/2203.07474)
* [An Empirical Study of Low Precision Quantization for TinyML](https://arxiv.org/abs/2203.05492)
* [Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks](https://arxiv.org/abs/2203.05025)
* [A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices](https://arxiv.org/abs/2203.04894)
* [P2M: A Processing-in-Pixel-in-Memory Paradigm for Resource-Constrained TinyML Applications](https://arxiv.org/abs/2203.04737)
* [Millimeter-Scale Ultra-Low-Power Imaging System for Intelligent Edge Monitoring](https://arxiv.org/abs/2203.04496)
* [Improving the Energy Efficiency and Robustness of tinyML Computer Vision using Log-Gradient Input Images](https://arxiv.org/abs/2203.02571)
* [Hardware Deployable Edge-AI Solution for Pre-screening of Oral Tongue Lesions using TinyML on Embedded Devices](https://ieeexplore.ieee.org/document/9737316)
* [TinyML: A Systematic Review and Synthesis of Existing Research](https://ieeexplore.ieee.org/document/9722636)
* [A review on TinyML: State-of-the-art and prospects](https://www.sciencedirect.com/science/article/pii/S1319157821003335)
* [Tiny Machine Learning (Tiny-ML) for Efficient Channel Estimation and Signal Detection](https://ieeexplore.ieee.org/abstract/document/9745826)
* [TinyMLedu: The Tiny Machine Learning Open Education Initiative](https://dl.acm.org/doi/10.1145/3478432.3499093)
* [Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications](https://dl.acm.org/doi/10.1145/3486618)
* [The Scale4Edge RISC-V ecosystem](https://dl.acm.org/doi/10.5555/3539845.3540037)
* [RedMulE: a compact FP16 matrix-multiplication accelerator for adaptive deep learning on RISC-V-based ultra-low-power SoCs](https://dl.acm.org/doi/10.5555/3539845.3540099)
* [Bioformers: embedding transformers for ultra-low power sEMG-based gesture recognition](https://dl.acm.org/doi/10.5555/3539845.3540180)
* [An On-Device Learning System for Estimating Liquid Consumption from Consumer-Grade Water Bottles and Its Evaluation](https://www.mdpi.com/1424-8220/22/7/2514)

### Feb. 2022(9)
* [tinyMAN: Lightweight Energy Manager using Reinforcement Learning for Energy Harvesting Wearable IoT Devices](https://arxiv.org/abs/2202.09297)
* [How to Manage Tiny Machine Learning at Scale: An Industrial Perspective](https://arxiv.org/abs/2202.09113)
* [A VM/Containerized Approach for Scaling TinyML Applications](https://arxiv.org/abs/2202.05057)
* [TinyM$^2$Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny Devices](https://arxiv.org/abs/2202.04303)
* [A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spotting](https://arxiv.org/abs/2202.02361)
* [BSC: Block-based Stochastic Computing to Enable Accurate and Efficient TinyML](https://ieeexplore.ieee.org/document/9712585)
* [Heterogeneous Memory Architecture Accommodating Processing-in-Memory on SoC for AIoT Applications](https://ieeexplore.ieee.org/document/9712544)
* [Time series analysis for temperature forecasting using TinyML](https://ieeexplore.ieee.org/document/9700573)
* [Development of a TinyML based four-chamber refrigerator (TBFCR) for efficiently storing pharmaceutical products: Case Study: Pharmacies in Rwanda](https://dl.acm.org/doi/10.1145/3529836.3529932)

### Jan. 2022(19)
* [UDC: Unified DNAS for Compressible TinyML Models](https://arxiv.org/abs/2201.05842)
* [PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++](https://arxiv.org/abs/2201.02863)
* [CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAs](https://arxiv.org/abs/2201.01863)
* [A Heterogeneous In-Memory Computing Cluster For Flexible End-to-End Inference of Real-World Deep Neural Networks](https://arxiv.org/abs/2201.01089)
* [Everything You wanted to Know about Smart Agriculture](https://arxiv.org/abs/2201.04754)
* [TinyML-Based Concept System Used to Analyze Whether the Face Mask Is Worn Properly in Battery-Operated Conditions](https://www.mdpi.com/2076-3417/12/1/484)
* [Tiny Generative Image Compression for Bandwidth-Constrained Sensor Applications](https://ieeexplore.ieee.org/document/9680093)
* [TinyML in Africa: Opportunities and Challenges](https://ieeexplore.ieee.org/document/9682107)
* [Evaluating the practical limitations of TinyML: an experimental approach](https://ieeexplore.ieee.org/document/9682101)
* [Insect biodiversity in agriculture using IoT: opportunities and needs for further research](https://ieeexplore.ieee.org/document/9682153)
* [Imbal-OL: Online Machine Learning from Imbalanced Data Streams in Real-world IoT](https://ieeexplore.ieee.org/document/9671765)
* [DeepQGHO: Quantized Greedy Hyperparameter Optimization in Deep Neural Networks for on-the-Fly Learning](https://ieeexplore.ieee.org/document/9676610)
* [Audio Distress Signal Recognition in Rural and Urban Areas using a WSN consisting of Portable Resource-Constrained Devices](https://ieeexplore.ieee.org/document/9665474)
* [Identification of Deadliest Mosquitoes Using Wing Beats Sound Classification on Tiny Embedded System Using Machine Learning and Edge Impulse Platform](https://ieeexplore.ieee.org/document/9662116)
* [Auritus: An Open-Source Optimization Toolkit for Training and Development of Human Movement Models and Filters Using Earables](https://dl.acm.org/doi/10.1145/3534586)
* [Towards Semantic Management of On-Device Applications in Industrial IoT](https://dl.acm.org/doi/10.1145/3510820)
* [PhiNets: a scalable backbone for low-power AI at the edge](https://dl.acm.org/doi/10.1145/3510832)
* [Roadmap for edge AI: a Dagstuhl perspective](https://dl.acm.org/doi/10.1145/3523230.3523235)
* [Energy Efficient Computing Systems: Architectures, Abstractions and Modeling to Techniques and Standards](https://dl.acm.org/doi/10.1145/3511094)

## 2021(88)

### Dec. 2021(17)
* [TinyML Platforms Benchmarking](https://arxiv.org/abs/2112.01319)
* [Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework ICCAD Special Session Paper](https://ieeexplore.ieee.org/document/9643539)
* [Special Session: Approximate TinyML Systems: Full System Approximations for Extreme Energy-Efficiency in Intelligent Edge Devices](https://ieeexplore.ieee.org/document/9643771)
* [A Dataset and TinyML Model for Coarse Age Classification Based on Voice Commands](https://ieeexplore.ieee.org/document/9642091)
* [Edge AI-based Respiratory Disease Recognition from Exhaled Breath Signatures](https://ieeexplore.ieee.org/document/9634140)
* [Intelligent Acoustic Module for Autonomous Vehicles using Fast Gated Recurrent approach](https://ieeexplore.ieee.org/document/9633681)
* [Resource Constrained CVD Classification Using Single Lead ECG On Wearable and Implantable Devices](https://ieeexplore.ieee.org/document/9630348)
* [Synthetic Exhaled Breath Data-Based Edge AI Model for the Prediction of Chronic Obstructive Pulmonary Disease](https://ieeexplore.ieee.org/document/9629420)
* [ML-based data classification and data aggregation on the edge](https://dl.acm.org/doi/10.1145/3488658.3493786)

### Nov. 2021(17)
* [RaScaNet: Learning Tiny Models by Raster-Scanning Images](https://ieeexplore.ieee.org/document/9577645)
* [arXiv - Energy-Efficient Inference on the Edge Exploiting TinyML Capabilities for UAVs](https://arxiv.org/abs/2111.15481)
* [MDPI - Energy-Efficient Inference on the Edge Exploiting TinyML Capabilities for UAVs](https://www.mdpi.com/2504-446X/5/4/127)
* [arXiv - TiWS-iForest: Isolation Forest in Weakly Supervised and Tiny ML scenarios](https://arxiv.org/abs/2111.15432)
* [sciencedirect - TiWS-iForest: Isolation forest in weakly supervised and tiny ML scenarios](https://www.sciencedirect.com/science/article/abs/pii/S0020025522008155)
* [BSC: Block-based Stochastic Computing to Enable Accurate and Efficient TinyML](https://arxiv.org/abs/2111.06686)
* [AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator](https://arxiv.org/abs/2111.06503)
* [Automated HW/SW Co-design for Edge AI: State, Challenges and Steps Ahead: Special Session Paper](https://ieeexplore.ieee.org/document/9603364)
* [An SRAM Optimized Approach for Constant Memory Consumption and Ultra-fast Execution of ML Classifiers on TinyML Hardware](https://ieeexplore.ieee.org/document/9592444)
* [A QKeras Neural Network Zoo for Deeply Quantized Imaging](https://ieeexplore.ieee.org/document/9597341)
* [Implementation of Cyber Threat Intelligence Platform on Internet of Things (IoT) using TinyML Approach for Deceiving Cyber Invasion](https://ieeexplore.ieee.org/document/9590959)
* [TinyML Benchmark: Executing Fully Connected Neural Networks on Commodity Microcontrollers](https://ieeexplore.ieee.org/document/9595024)
* [TinyML: Current Progress, Research Challenges, and Future Roadmap](https://ieeexplore.ieee.org/document/9586232)
* [Real-Time Activity Tracking using TinyML to Support Elderly Care](https://ieeexplore.ieee.org/document/9579991)
* [Cartoonize Images using TinyML Strategies with Transfer Learning](https://ieeexplore.ieee.org/document/9581835)
* [A Review of Machine Learning and TinyML in Healthcare](https://dl.acm.org/doi/10.1145/3503823.3503836)
* [Hardware/Software Co-Design for TinyML Voice-Recognition Application on Resource Frugal Edge Devices](https://www.mdpi.com/2076-3417/11/22/11073)

### Oct. 2021(10)
* [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://arxiv.org/abs/2110.15352)
* [Micronets: Neural network architectures for deploying tinyml applications on commodity microcontrollers](https://arxiv.org/abs/2010.11267)
* [arXiv - A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays](https://arxiv.org/abs/2110.10486)
* [IEEE - A TinyML Platform for On-Device Continual Learning With Quantized Latent Replays](https://ieeexplore.ieee.org/document/9580920)
* [TrafficNNode: Low Power Vehicle Sensing Platform for Smart Cities](https://ieeexplore.ieee.org/document/9556173)
* [TinyFedTL: Federated Transfer Learning on Tiny Devices](https://arxiv.org/abs/2110.01107)
* [TinyML Meets IoT: A Comprehensive Survey](https://www.sciencedirect.com/science/article/abs/pii/S2542660521001025)
* [Design of a Novel Neural Network Compression Method for Tiny Machine Learning](https://dl.acm.org/doi/10.1145/3501409.3501526)
* [Intermittent-Aware Neural Architecture Search](https://dl.acm.org/doi/10.1145/3476995)
* [Trends in Intelligent Communication Systems: Review of Standards, Major Research Projects, and Identification of Research Gaps](https://www.mdpi.com/2224-2708/10/4/60)

### Sep. 2021(8)
* [MbedML: A Machine Learning Project for Embedded Systems](http://sedici.unlp.edu.ar/handle/10915/125142)
* [TinyML Benchmark: Executing Fully Connected Neural Networks on Commodity Microcontrollers](https://ieeexplore.ieee.org/document/9595024)
* [TinyOL: TinyML with Online-Learning on Microcontrollers](https://ieeexplore.ieee.org/document/9533927)
* [Design of a Speech Anger Recognition System on Arduino Nano 33 BLE Sense](https://ieeexplore.ieee.org/document/9526323)
* [A Microcontroller is All You Need: Enabling Transformer Execution on Low-Power IoT Endnodes](https://ieeexplore.ieee.org/document/9524173)
* [Capacitive Sensing Based On-board Hand Gesture Recognition with TinyML](https://dl.acm.org/doi/10.1145/3460418.3479287)
* [Automated HW/SW co-design for edge AI: state, challenges and steps ahead](https://dl.acm.org/doi/10.1145/3478684.3479261)
* [On-Device Training of Machine Learning Models on Microcontrollers With a Look at Federated Learning](https://dl.acm.org/doi/10.1145/3462203.3475896)

### Jly. 2021(4)
* [Supporting AI Engineering on the IoT Edge through Model-Driven TinyML](https://arxiv.org/abs/2107.02690)
* [An Unsupervised TinyML Approach Applied for Pavement Anomalies Detection Under the Internet of Intelligent Vehicles](https://ieeexplore.ieee.org/document/9488546)
* [Integer-Only Approximated MFCC for Ultra-Low Power Audio NN Processing on Multi-Core MCUs](https://ieeexplore.ieee.org/document/9458491)
* [LPWAN and Embedded Machine Learning as Enablers for the Next Generation of Wearable Devices](https://www.mdpi.com/1424-8220/21/15/5218)

### Jun. 2021(9)
* [LB-CNN: An Open Source Framework for Fast Training of Light Binary Convolutional Neural Networks using Chainer and Cupy](https://arxiv.org/abs/2106.15350)
* [TinyML: Analysis of Xtensa LX6 microprocessor for Neural Network Applications by ESP32 SoC](https://arxiv.org/abs/2106.10652)
* [MLPerf Tiny Benchmark](https://arxiv.org/abs/2106.07597)
* [Widening Access to Applied Machine Learning with TinyML](https://arxiv.org/abs/2106.04008)
* [TinyML, Anomaly Detection](https://scholarworks.csun.edu/handle/10211.3/219966)
* [An Evolving TinyML Compression Algorithm for IoT Environments Based on Data Eccentricity](https://www.mdpi.com/1424-8220/21/12/4153)
* [The synergy of complex event processing and tiny machine learning in industrial IoT](https://dl.acm.org/doi/10.1145/3465480.3466928)
* [An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications](https://www.mdpi.com/1424-8220/21/13/4412)
* [An Evolving TinyML Compression Algorithm for IoT Environments Based on Data Eccentricity](https://www.mdpi.com/1424-8220/21/12/4153)

### May 2021(7)
* [The Synergy of Complex Event Processing and Tiny Machine Learning in Industrial IoT](https://arxiv.org/abs/2105.03371)
* [TinyML benchmark: Executing fully connected neural networks on commodity microcontrollers](https://www.researchgate.net/publication/351527145_TinyML_Benchmark_Executing_Fully_Connected_Neural_Networks_on_Commodity_Microcontrollers)
* [Comparing Industry Frameworks with Deeply Quantized Neural Networks on Microcontrollers](https://ieeexplore.ieee.org/document/9427638)
* [Putting AI on Diet: TinyML and Efficient Deep Learning](https://ieeexplore.ieee.org/document/9427348)
* [A TinyMLaaS Ecosystem for Machine Learning in IoT: Overview and Research Challenges](https://ieeexplore.ieee.org/document/9427352)
* [Adaptive Traffic Control With TinyML](https://ieeexplore.ieee.org/document/9419472)
* [Performance of deep neural networks on low-power IoT devices](https://dl.acm.org/doi/10.1145/3458473.3458823)

### Apr. 2021(6)
* [AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge](https://arxiv.org/abs/2104.14623)
* [Measuring what Really Matters: Optimizing Neural Networks for TinyML](https://arxiv.org/abs/2104.10645)
* [Compiler Toolchains for Deep Learning Workloads on Embedded Platforms](https://arxiv.org/abs/2104.04576)
* [TENT: Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT](https://arxiv.org/abs/2104.02233)
* [Robustifying the Deployment of tinyML Models for Autonomous Mini-Vehicles](https://ieeexplore.ieee.org/document/9401154)
* [μNAS: Constrained Neural Architecture Search for Microcontrollers](https://dl.acm.org/doi/10.1145/3437984.3458836)

### Mar. 2021(11)
* [TinyOL: TinyML with Online-Learning on Microcontrollers](https://arxiv.org/abs/2103.08295)
* [Hypervector Design for Efficient Hyperdimensional Computing on Edge Devices](https://arxiv.org/abs/2103.06709)
* [Smartphone Impostor Detection with Behavioral Data Privacy and Minimalist Hardware Support](https://arxiv.org/abs/2103.06453)
* [Quantization-Guided Training for Compact TinyML Models](https://arxiv.org/abs/2103.06231)
* [hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices](https://arxiv.org/abs/2103.05579)
* [Memory-Efficient, Limb Position-Aware Hand Gesture Recognition using Hyperdimensional Computing](https://arxiv.org/abs/2103.05267)
* [An Ultra-low Power RNN Classifier for Always-On Voice Wake-Up Detection Robust to Real-World Scenarios](https://arxiv.org/abs/2103.04792)
* [SWIS -- Shared Weight bIt Sparsity for Efficient Neural Network Acceleration](https://arxiv.org/abs/2103.01308)
* [Characterization of Neural Networks Automatically Mapped on Automotive-grade Microcontrollers](https://arxiv.org/abs/2103.00201)
* [IoT-based smart triage of Covid-19 suspicious cases in the Emergency Department](https://ieeexplore.ieee.org/document/9367584)
* [Automating Tiny ML Intelligent Sensors DevOPS Using Microsoft Azure](https://ieeexplore.ieee.org/document/9377755)

### Feb. 2021(4)
* [Robustifying the Deployment of tinyML Models for Autonomous Mini-Vehicles](https://www.mdpi.com/1424-8220/21/4/1339)
* [TinyML for Ubiquitous Edge AI](https://arxiv.org/abs/2102.01255)
* [Robustifying the Deployment of tinyML Models for Autonomous Mini-Vehicles](https://www.mdpi.com/1424-8220/21/4/1339)
* [Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications](https://www.mdpi.com/2224-2708/10/1/13)

### Jan. 2021(3)
* [Rethinking Generalization in American Sign Language Prediction for Edge Devices with Extremely Low Memory Footprint](https://ieeexplore.ieee.org/document/9332480)
* [Toward Data-Adaptable TinyML using Model Partial Replacement for Resource Frugal Edge Device](https://dl.acm.org/doi/10.1145/3432261.3439865)
* [A 0.57-GOPS/DSP Object Detection PIM Accelerator on FPGA](https://dl.acm.org/doi/10.1145/3394885.3431659)

## 2020(29)

### Dec. 2020(8)
* [Online On-device MCU Transfer Learning](https://vikramramanathan.com/portfolio/portfolio-mcu-tf/)
* [A VM/Containerized Approach for Scaling TinyML Applications](https://openreview.net/forum?id=m7Aqzt7Xf4S)
* [Resource Efficient Deep Reinforcement Learning for Acutely Constrained TinyML Devices](https://openreview.net/forum?id=_vo8DFo9iuB)
* [Deep Learning for Compute in Memory](https://openreview.net/forum?id=zEJDxAKKiat)
* [Does Form Follow Function? An Empirical Exploration of the Impact of Deep Neural Network Architecture Design on Hardware-Specific Acceleration](https://openreview.net/forum?id=-iuG__7I9QE)
* [TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss](https://openreview.net/forum?id=LYzEISv1bre)
* [Privacy-Preserving Inference on the Edge: Mitigating a New Threat Model](https://openreview.net/forum?id=rlHeH9tx3SM)
* [Mini-NAS: A Neural Architecture Search Framework for Small Scale Image Classification Applications](https://openreview.net/forum?id=ERhIA5Y7IaT)

### Nov. 2020(2)
* [Tiny Neural Networks for Environmental Predictions: an integrated approach with Miosix](https://ieeexplore.ieee.org/abstract/document/9239623)
* [Starfish: resilient image compression for AIoT cameras](https://dl.acm.org/doi/10.1145/3384419.3430769)

### Oct. 2020(2)
* [MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers](https://arxiv.org/abs/2010.11267)
* [TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems](https://arxiv.org/abs/2010.08678)

### Sep. 2020(4)
* [Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware](https://arxiv.org/abs/2009.04465)
* [AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers](https://arxiv.org/abs/2009.14385)
* [Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware](https://arxiv.org/abs/2009.04465)
* [FUDGE: a frugal edge node for advanced IoT solutions in contexts with limited resources](https://dl.acm.org/doi/10.1145/3410670.3410857)

### Aug. 2020(2)
* [TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices](https://arxiv.org/abs/2008.04245)
* [TinyML-Enabled Frugal Smart Objects: Challenges and Opportunities](https://ieeexplore.ieee.org/document/9166461)

### Jul. 2020(5)
* [Robustifying the Deployment of tinyML Models for Autonomous mini-vehicles](https://arxiv.org/abs/2007.00302)
* [Benchmarking TinyML Systems: Challenges and Direction](https://arxiv.org/abs/2003.04821)
* [MCUNet: Tiny Deep Learning on IoT Devices](https://arxiv.org/abs/2007.10319)
* [Bringing machine learning to the deepest IoT edge with TinyML as-a-service](https://www.researchgate.net/publication/342916900_Bringing_Machine_Learning_to_the_Deepest_IoT_Edge_with_TinyML_as-a-Service)
* [Optimizing Machine Learning Inference
for MCU:s](https://lup.lub.lu.se/student-papers/search/publication/9026280)

### Jun. 2020(1)
* [Welcome Message from SenSys-ML'20 Chairs](https://ieeexplore.ieee.org/document/9111711)

### May 2020(1)
* [AI Neural Networks Inference into the IoT Embedded Devices using TinyML for Pattern Detection within a Security System](https://www.researchgate.net/publication/347873825_AI_NEURAL_NETWORKS_INFERENCE_INTO_THE_IOT_EMBEDDED_DEVICES_USING_TINYML_FOR_PATTERN_DETECTION_WITHIN_A_SECURITY_SYSTEM)

### Mar. 2020(2)
* [Benchmarking TinyML Systems: Challenges and Direction](https://arxiv.org/abs/2003.04821)
* [CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices](https://ieeexplore.ieee.org/document/9049084)

### Feb. 2020(1)
* [FANN-on-MCU: An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things](https://ieeexplore.ieee.org/document/9016202)

### Jan. 2020(1)
* [Alcohol Sensor Calibration on the Edge Using Tiny Machine Learning (Tiny-ML) Hardware](https://iopscience.iop.org/article/10.1149/MA2020-01261848mtgabs/meta)

## 2019(5)

### Nov. 2019(2)
* [On-Device Machine Learning: An Algorithms and Learning Theory Perspective](https://arxiv.org/abs/1911.00623)
* [Emotion Filtering at the Edge](https://dl.acm.org/doi/10.1145/3362743.3362960)

### Oct. 2019(1)
* [Neural networks on microcontrollers: saving memory at inference via operator reordering](https://arxiv.org/abs/1910.05110)

### Sep. 2019(2)
* [Book - TinyML](https://tinymlbook.com/wp-content/uploads/2020/11/TinyML_preview.pdf)
* [Class-dependent Compression of Deep Neural Networks](https://arxiv.org/abs/1909.10364)

## 2003(1)
* [TinyML: Meta-data for Wireless Networks](https://people.eecs.berkeley.edu/~culler/cs294-f03/finalpapers/tinyml.pdf)

---
**資料來源：[Google Scholar](https://scholar.google.com.tw/)、[arXiv](https://arxiv.org/)、[ResearchGate](https://www.researchgate.net/)、[IEEE Xplore](https://ieeexplore.ieee.org/)、[ACM Digital Library](https://dl.acm.org/)、[MDPI](https://www.mdpi.com/)、[ScienceDirect](https://www.sciencedirect.com/)、[OpenReview](https://openreview.net/)等**

---
OmniXRI 整理製作，歡迎點贊、收藏、訂閱、留言、分享，

###### tags: `TinyML`