{"id":13769176,"url":"https://github.com/gigwegbe/tinyml-papers-and-projects","last_synced_at":"2025-05-11T01:31:44.518Z","repository":{"id":37007867,"uuid":"324236305","full_name":"gigwegbe/tinyml-papers-and-projects","owner":"gigwegbe","description":"This is a list of interesting papers and projects about TinyML. ","archived":false,"fork":false,"pushed_at":"2025-01-09T12:25:21.000Z","size":288,"stargazers_count":864,"open_issues_count":4,"forks_count":148,"subscribers_count":62,"default_branch":"main","last_synced_at":"2025-05-07T09:53:31.314Z","etag":null,"topics":["computer-vision","embedded-systems","machine-learning","neural-architecture-search","tinyml","wake-word"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gigwegbe.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-12-24T21:06:57.000Z","updated_at":"2025-05-07T02:21:03.000Z","dependencies_parsed_at":"2023-01-17T12:47:54.660Z","dependency_job_id":"40af6392-80ac-4c5a-adc4-ae329397d1a9","html_url":"https://github.com/gigwegbe/tinyml-papers-and-projects","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gigwegbe%2Ftinyml-papers-and-projects","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gigwegbe%2Ftinyml-papers-and-projects/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gigwegbe%2Ftinyml-papers-and-projects/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gigwegbe%2Ftinyml-papers-and-projects/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gigwegbe","download_url":"https://codeload.github.com/gigwegbe/tinyml-papers-and-projects/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253504550,"owners_count":21918830,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","embedded-systems","machine-learning","neural-architecture-search","tinyml","wake-word"],"created_at":"2024-08-03T17:00:18.590Z","updated_at":"2025-05-11T01:31:44.511Z","avatar_url":"https://github.com/gigwegbe.png","language":null,"funding_links":[],"categories":["Uncategorized","Papers","TODO","其他_机器学习与深度学习","三、实用资源：从入门到进阶"],"sub_categories":["Uncategorized","Survey","3. 技术与项目参考"],"readme":"## TinyML Papers and Projects\n\u003e TinyML is awesome.\n\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re) [![Contributions](https://img.shields.io/github/issues-pr-closed-raw/gigwegbe/tinyml-papers-and-projects.svg?label=contributions)](https://github.com/gigwegbe/tinyml-papers-and-projects/pulls) [![Commits](https://img.shields.io/github/last-commit/gigwegbe/tinyml-papers-and-projects.svg?label=last%20contribution)](https://github.com/gigwegbe/tinyml-papers-and-projects/commits/main)\n\nThis is a list of interesting papers, projects, articles and talks about TinyML.\n\n- [Awesome Papers](#awesome-papers-): [2016](#2016) | [2017](#2017) | [2018](#2018) | [2019](#2019) | [2020](#2020) | [2022](#2022) | [2023](#2023) | [2024](#2024) | [2025](#2025)\n- [Awesome Projects](#awesome-tinyml-projects): [Projects Source code](#projects-source-code) | [Projects Articles](#projects-articles)\n- [Benchmarking](#benchmarking)\n- Resources\n  - [Articles](#articles)\n  - [Books](#books)\n  - [Libraries and Tools](#libraries-and-tools)\n  - [Courses](#courses)\n  - [TinyML Talks](#tinyml-talks--conferences)\n- [Contact \u0026 Feedback](#contact--feedback)\n\n## Awesome Papers \n\n### \u003cins\u003e**2016**\u003c/ins\u003e\n\n- DEEP COMPRESSION: COMPRESSING DEEP NEURAL NETWORKS WITH PRUNING, TRAINED QUANTIZATION AND HUFFMAN CODING | [`[pdf]`](https://arxiv.org/pdf/1510.00149.pdf)\n- **[SQUEEZENET]** ALEXNET-LEVEL ACCURACY WITH50X FEWER PARAMETERS AND \u003c0.5MB MODEL SIZE | [`[pdf]`](https://arxiv.org/pdf/1602.07360.pdf)\n\n### \u003cins\u003e**2017**\u003c/ins\u003e\n\n- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference | [`[pdf]`](https://arxiv.org/pdf/1712.05877.pdf)\n- Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things  | [`[pdf]`](https://www.microsoft.com/en-us/research/uploads/prod/2017/06/kumar17.pdf)\n- ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices  | [`[pdf]`](https://www.microsoft.com/en-us/research/uploads/prod/2017/06/protonn.pdf)\n- OPENMV: A PYTHON POWERED, EXTENSIBLE MACHINE VISION CAMERA | [`[pdf]`](https://arxiv.org/pdf/1711.10464.pdf) [`[official code]`]( https://github.com/openmv/openmv.git)\n\n### \u003cins\u003e**2018**\u003c/ins\u003e\n\n- **[AMC]** AutoML for Model Compression and Acceleration on Mobile Devices | [`[pdf]`](https://arxiv.org/pdf/1802.03494.pdf) [`[official code]`](https://github.com/mit-han-lab/amc)\n- Mobile Machine Learning Hardware at ARM: A Systems-on-Chip (SoC) Perspective | [`[pdf]`](https://arxiv.org/pdf/1801.06274.pdf)\n- **[HAQ]** Hardware-Aware Automated Quantization with Mixed Precision | [`[pdf]`](https://arxiv.org/abs/1811.08886)\n- Efficient and Robust Machine Learning for Real-World Systems | [`[pdf]`](https://arxiv.org/pdf/1812.02240.pdf)\n- **[GesturePod]** Gesture-based Interaction Cane for People with Visual Impairments | [`[pdf]`](https://www.microsoft.com/en-us/research/uploads/prod/2018/05/CHI19_GesturePod.pdf)\n- **[YOLO-LITE]** A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers | [`[pdf]`](https://arxiv.org/pdf/1811.05588v1.pdf)\n- **[CMSIS-NN]** Efficient Neural Network Kernels for Arm Cortex-M CPUs | [`[pdf]`](https://arxiv.org/pdf/1801.06601.pdf)\n- Quantizing deep convolutional networks for efficient inference: A whitepaper | [`[pdf]`](https://arxiv.org/pdf/1806.08342.pdf)\n- **[Hello Edge]** Keyword Spotting on Microcontrollers | [`[pdf]`](https://arxiv.org/pdf/1711.07128.pdf)\n\n  | ▲ [Top](#tinyml-papers-and-projects) |\n  | ------------------------------------ |\n\n### \u003cins\u003e**2019**\u003c/ins\u003e\n\n- FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network | [`[pdf]`](https://arxiv.org/pdf/1901.02358.pdf)\n- Image Classification on IoT Edge Devices: Profiling and Modeling| [`[pdf]`](https://arxiv.org/pdf/1902.11119.pdf)\n- **[PROXYLESSNAS]** DIRECT NEURAL ARCHITECTURE SEARCH ON TARGET TASK AND HARDWARE |[`[pdf]`](https://arxiv.org/pdf/1812.00332.pdf) [`[official code]`](https://github.com/mit-han-lab/proxylessnas)\n- Energy Efficient Hardware for On-Device CNN Inference via Transfer Learning | [`[pdf]`](https://arxiv.org/pdf/1812.01672.pdf)\n- Visual Wake Words Dataset | [`[pdf]`](https://arxiv.org/pdf/1906.05721.pdf)\n- Compiling KB-Sized Machine Learning Models to Tiny IoT Devices | [`[pdf]`](microsoft.com/en-us/research/uploads/prod/2018/10/pldi19-SeeDot.pdf)\n- Reconfigurable Multitask Audio Dynamics Processing Scheme | [`[pdf]`](https://arxiv.org/abs/1903.06392 )\n- Pushing the limits of RNN Compression | [`[pdf]`](https://arxiv.org/pdf/1910.02558.pdf)\n- A low-power end-to-end hybrid neuromorphic framework for surveillance applications | [`[pdf]`](https://arxiv.org/pdf/1910.09806.pdf)\n- Deep Learning at the Edge | [`[pdf]`](https://arxiv.org/pdf/1910.10231.pdf)\n- Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers | [`[pdf]`](https://arxiv.org/pdf/1905.13082.pdf) [`[official code]`](https://github.com/EEESlab/CMix-NN)\n- **[SpArSe]** Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers  |[`[pdf]`](https://arxiv.org/pdf/1905.12107.pdf)\n- **[MobileNetV2]** Inverted Residuals and Linear Bottlenecks |[`[pdf]`](https://arxiv.org/pdf/1801.04381.pdf)\n- Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization  |[`[pdf]`](https://arxiv.org/pdf/1906.02107.pdf)\n- Low-Power Computer Vision: Status, Challenges, Opportunities |[`[pdf]`](https://arxiv.org/pdf/1904.07714.pdf)\n\n  | ▲ [Top](#tinyml-papers-and-projects) |\n  | ------------------------------------ |\n\n### \u003cins\u003e**2020**\u003c/ins\u003e\n\n- COMPRESSING RNNS FOR IOT DEVICES BY 15-38X USING KRONECKER PRODUCTS |[`[pdf]`](https://arxiv.org/pdf/1906.02876.pdf)\n- BENCHMARKING TINYML SYSTEMS: CHALLENGES AND DIRECTION |[`[pdf]`](https://arxiv.org/pdf/2003.04821v3.pdf)\n- Lite Transformer with Long-Short Range Attention |[`[pdf]`](https://arxiv.org/pdf/2004.11886.pdf)\n- **[FANN-on-MCU]** An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things |[`[pdf]`](https://arxiv.org/pdf/1911.03314.pdf)\n- **[TENSORFLOW LITE MICRO]** EMBEDDED MACHINE LEARNING ON TINYML SYSTEMS |[`[pdf]`](https://arxiv.org/pdf/2010.08678v2.pdf)\n- **[AttendNets]** Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers |[`[pdf]`](https://arxiv.org/pdf/2009.14385v1.pdf)\n- **[TinySpeech]** Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices |[`[pdf]`](https://arxiv.org/pdf/2008.04245v6.pdf)\n- Robust navigation with tinyML for autonomous mini-vehicles |[`[pdf]`](https://arxiv.org/pdf/2007.00302v1.pdf) [`[official code]`](https://github.com/praesc/Robust-navigation-with-TinyML)\n- **[MICRONETS]** NEURAL NETWORK ARCHITECTURES FOR DEPLOYING TINYML APPLICATIONS ON COMMODITY MICROCONTROLLERS |[`[pdf]`](https://arxiv.org/pdf/2010.11267v2.pdf)\n- **[TinyLSTMs]** Efficient Neural Speech Enhancement for Hearing Aids |[`[pdf]`](https://arxiv.org/pdf/2005.11138.pdf)\n- **[MCUNet]** Tiny Deep Learning on IoT Devices |[`[pdf]`](https://arxiv.org/abs/2007.10319) [`[official code]`](https://github.com/mit-han-lab/mcunet)\n- Efficient Residue Number System Based Winograd Convolution | [`[pdf]`](https://arxiv.org/pdf/2007.12216.pdf)\n- INTEGER QUANTIZATION FOR DEEP LEARNING INFERENCE: PRINCIPLES AND EMPIRICAL EVALUATION  | [`[pdf]`](https://arxiv.org/pdf/2004.09602)\n- On Front-end Gain Invariant Modeling for Wake Word Spotting | [`[pdf]`](https://arxiv.org/pdf/2010.06676.pdf)\n- TOWARDS DATA-EFFICIENT MODELING FOR WAKE WORD SPOTTING | [`[pdf]`](https://arxiv.org/pdf/2010.06659.pdf)\n- Accurate Detection of Wake Word Start and End Using a CNN | [`[pdf]`](https://arxiv.org/pdf/2008.03790.pdf)\n- **[PoPS]** Policy Pruning and Shrinking for Deep Reinforcement Learning | [`[pdf]`](https://arxiv.org/pdf/2001.05012.pdf)\n- Howl: A Deployed, Open-Source Wake Word Detection System | [`[pdf]`](https://arxiv.org/pdf/2008.09606.pdf) [`[official code]`](https://github.com/castorini/howl)\n- **[LeakyPick]** IoT Audio Spy Detector | [`[pdf]`](https://arxiv.org/pdf/2007.00500.pdf)\n- On-Device Machine Learning: An Algorithms and Learning Theory Perspective  | [`[pdf]`](https://arxiv.org/pdf/1911.00623.pdf)\n- Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers | [`[pdf]`](https://arxiv.org/pdf/2008.05124.pdf)\n- OPTIMIZE WHAT MATTERS: TRAINING DNN-HMM KEYWORD SPOTTING MODEL USING END METRIC | [`[pdf]`](https://arxiv.org/pdf/2011.01151.pdf)\n- **[RNNPool]** Efficient Non-linear Pooling for RAM Constrained Inference | [`[blog]`](https://www.microsoft.com/en-us/research/blog/seeing-on-tiny-battery-powered-microcontrollers-with-rnnpool/?utm_medium=email\u0026_hsmi=104017359\u0026_hsenc=p2ANqtz-_DVkWnyh_NhAV6j4hTFngepUyiNjZ5GO5CYIQfpl5NzerjwxOBQcpdkilzGpt9ic4HglvgM80h7wIkFNX89xe-3_j7Kw\u0026utm_content=104017359\u0026utm_source=hs_email)  [`[pdf]`](https://arxiv.org/pdf/2002.11921.pdf) [`[official code]`](https://github.com/microsoft/EdgeML/blob/master/pytorch/edgeml_pytorch/graph/rnnpool.py)\n- **[Shiftry]** RNN Inference in 2KB of RAM |[`[pdf]`](https://www.microsoft.com/en-us/research/uploads/prod/2020/10/oopsla20main-p230-p-aba27a6-48263M-final.pdf)\n- **[Once for All]** Train One Network and Specialize it for Efficient Deployment  |[`[pdf]`](https://arxiv.org/pdf/1908.09791.pdf) [`[official code]`](https://github.com/mit-han-lab/once-for-all)\n- A Tiny CNN Architecture for Medical Face Mask Detection for Resource-Constrained Endpoints  |[`[pdf]`](https://arxiv.org/pdf/2011.14858.pdf)\n- Rethinking Generalization in American Sign Language Prediction for Edge Devices with Extremely Low Memory Footprint |[`[pdf]`](https://arxiv.org/pdf/2011.13741.pdf) [`[presentation]`](https://www.youtube.com/watch?v=bJ1vnhAbJ9o\u0026feature=youtu.be)\n- **[ShadowNet]** A Secure and Efficient System for On-device Model Inference |[`[pdf]`](https://arxiv.org/pdf/2011.05905.pdf)\n- Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware |[`[pdf]`](https://arxiv.org/pdf/2009.04465.pdf)\n- Automated facial recognition for wildlife that lack unique markings: A deep learning approach for brown bears  |[`[pdf]`](https://onlinelibrary.wiley.com/doi/epdf/10.1002/ece3.6840)\n- **[HyNNA]**: Improved Performance for Neuromorphic Vision Sensor based Surveillance\nusing Hybrid Neural Network Architecture |[`[pdf]`](https://arxiv.org/pdf/2003.08603.pdf)\n- The Hardware Lottery |[`[pdf]`](https://arxiv.org/pdf/2009.06489.pdf)\n- MLPerf Inference Benchmark |[`[pdf]`](https://arxiv.org/pdf/1911.02549.pdf)\n- MLPerf Mobile Inference Benchmark : Why Mobile AI Benchmarking Is Hard and What to Do About It |[`[pdf]`](https://arxiv.org/pdf/2012.02328.pdf)\n- **[TinyRL]** Learning to Seek: Tiny Robot Learning for Source Seeking on a Nano Quadcopter |[`[pdf]`](https://arxiv.org/pdf/1909.11236.pdf) [`[presentation]`](https://youtu.be/wmVKbX7MOnU)\n- Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point |[`[pdf]`](https://proceedings.neurips.cc//paper/2020/file/747e32ab0fea7fbd2ad9ec03daa3f840-Paper.pdf)\n- **[TinyBERT]** Distilling BERT for Natural Language Understanding  |[`[pdf]`](https://arxiv.org/pdf/1909.10351.pdf)\n- **[Larq]** An Open-Source Library for Training Binarized Neural Networks |[`[pdf]`](https://arxiv.org/pdf/2011.09398.pdf) [`[presentation]`](https://www.youtube.com/watch?v=f9SNqDejOB0) [`[official code]`](https://github.com/larq/larq)\n- **[FedML]** A Research Library and Benchmark for Federated Machine Learning  |[`[pdf]`](https://arxiv.org/pdf/2007.13518.pdf)\n- Survey of Machine Learning Accelerators  |[`[pdf]`](https://arxiv.org/pdf/2009.00993.pdf)\n\n  | ▲ [Top](#tinyml-papers-and-projects) |\n  | ------------------------------------ |\n\n### \u003cins\u003e**2021**\u003c/ins\u003e\n\n- **[I-BERT]** Integer-only BERT Quantization |[`[pdf]`](https://arxiv.org/pdf/2101.01321.pdf)\n- **[TinyTL]** Reduce Memory, Not Parameters for Efficient On-Device Learning |[`[pdf]`](https://arxiv.org/pdf/2007.11622.pdf) [`[official code]`](https://github.com/mit-han-lab/tinyml/tree/master/tinytl)\n- ON THE QUANTIZATION OF RECURRENT NEURAL NETWORKS |[`[pdf]`](https://arxiv.org/pdf/2101.05453.pdf)\n- **[TINY TRANSDUCER]** A HIGHLY-EFFICIENT SPEECH RECOGNITION MODEL ON EDGE DEVICES |[`[pdf]`](https://arxiv.org/pdf/2101.06856.pdf)\n- LARQ COMPUTE ENGINE: DESIGN, BENCHMARK, AND DEPLOY STATE-OF-THE-ART BINARIZED NEURAL NETWORKS |[`[pdf]`](https://arxiv.org/pdf/2011.09398.pdf)\n- **[LEAF]** A LEARNABLE FRONTEND FOR AUDIO CLASSIFICATION |[`[pdf]`](https://arxiv.org/pdf/2101.08596.pdf)\n- Enabling Large NNs on Tiny MCUs with Swapping |[`[pdf]`](https://arxiv.org/pdf/2101.08744.pdf)\n- Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms |[`[pdf]`](https://arxiv.org/pdf/2102.02147.pdf)\n- Estimating indoor occupancy through low-cost BLE devices |[`[pdf]`](https://arxiv.org/pdf/2102.03351.pdf)\n- **[Tiny Eats]** Eating Detection on a Microcontroller |[`[pdf]`](https://arxiv.org/pdf/2003.06699.pdf)\n- **[DEVICETTS]** A SMALL-FOOTPRINT, FAST, STABLE NETWORK FOR ON-DEVICE TEXT-TO-SPEECH |[`[pdf]`](https://arxiv.org/pdf/2010.15311.pdf)\n- A 0.57-GOPS/DSP Object Detection PIM Accelerator on FPGA |[`[pdf]`](https://dl.acm.org/doi/pdf/10.1145/3394885.3431659)\n- Rethinking Co-design of Neural Architectures and Hardware Accelerators |[`[pdf]`](https://arxiv.org/pdf/2102.08619.pdf)\n- Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks |[`[pdf]`](https://arxiv.org/pdf/2102.00554.pdf)\n- **[Apollo]** Transferable Architecture Exploration |[`[pdf]`](https://arxiv.org/pdf/2102.01723.pdf)\n- DEEP NEURAL NETWORK BASED COUGH DETECTION USING BED-MOUNTED ACCELEROMETER MEASUREMENTS |[`[pdf]`](https://arxiv.org/pdf/2102.04997.pdf)\n- TapNet: The Design, Training, Implementation, and Applications of a Multi-Task Learning CNN for Off-Screen Mobile Input|[`[pdf]`](https://arxiv.org/pdf/2102.09087.pdf)\n- MEMORY-EFFICIENT SPEECH RECOGNITION ON SMART DEVICES |[`[pdf]`](https://arxiv.org/pdf/2102.11531.pdf)\n- SWIS - Shared Weight bIt Sparsity for Efficient Neural Network Acceleration |[`[pdf]`](https://arxiv.org/pdf/2103.01308.pdf)\n- Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware |[`[pdf]`](https://arxiv.org/pdf/2009.04465.pdf)\n- Hypervector Design for Efficient Hyperdimensional Computing on Edge Devices  |[`[pdf]`](https://arxiv.org/pdf/2103.06709.pdf)\n- When Being Soft Makes You Tough:A Collision Resilient Quadcopter Inspired by Arthropod Exoskeletons |[`[pdf]`](https://arxiv.org/pdf/2103.04423.pdf)\n- **[TinyOL]** TinyML with Online-Learning on Microcontrollers |[`[pdf]`](https://arxiv.org/pdf/2103.08295.pdf)\n- Quantization-Guided Training for Compact TinyML Models |[`[pdf]`](https://arxiv.org/pdf/2103.06231.pdf)\n- hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices |[`[pdf]`](https://arxiv.org/pdf/2103.05579.pdf)\n- Memory-Efficient, Limb Position-Aware Hand Gesture Recognition using Hyperdimensional Computing |[`[pdf]`](https://arxiv.org/pdf/2103.05267.pdf)\n- Dynamically Throttleable Neural Networks(TNN) |[`[pdf]`](https://arxiv.org/pdf/2011.02836.pdf)\n- A Comprehensive Survey on Hardware-Aware Neural Architecture Search |[`[pdf]`](https://arxiv.org/pdf/2101.09336.pdf)\n- An Intelligent Bed Sensor System for Non-Contact Respiratory Rate Monitoring |[`[pdf]`](https://arxiv.org/pdf/2103.13792.pdf)\n- Measuring what Really Matters: Optimizing Neural Networks for TinyML |[`[pdf]`](https://arxiv.org/pdf/2104.10645.pdf)\n- Few-Shot Keyword Spotting in Any Language |[`[pdf]`](https://arxiv.org/pdf/2104.01454.pdf)\n- DOPING: A TECHNIQUE FOR EXTREME COMPRESSION OF LSTM MODELS USING SPARSE STRUCTURED ADDITIVE MATRICES |[`[pdf]`](https://proceedings.mlsys.org/paper/2021/file/a3f390d88e4c41f2747bfa2f1b5f87db-Paper.pdf)\n- **[OutlierNets]** Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection |[`[pdf]`](https://arxiv.org/pdf/2104.00528.pdf)\n- **[TENT]** Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT |[`[pdf]`](https://arxiv.org/pdf/2104.02233.pdf)\n- A 1D-CNN Based Deep Learning Technique for Sleep Apnea Detection in IoT Sensors  |[`[pdf]`](https://arxiv.org/pdf/2105.00528.pdf)\n- ADAPTIVE TEST-TIME AUGMENTATION FOR LOW-POWER CPU |[`[pdf]`](https://arxiv.org/pdf/2105.06183.pdf)\n- Compiler Toolchains for Deep Learning Workloads on Embedded Platforms |[`[pdf]`](https://arxiv.org/pdf/2104.04576.pdf)\n- **[ProxiMic]** Convenient Voice Activation via Close-to-Mic Speech Detected by a Single Microphone |[`[pdf]`](https://dl.acm.org/doi/pdf/10.1145/3411764.3445687)\n- **[Fusion-DHL]** WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments |[`[pdf]`](https://arxiv.org/pdf/2105.08837.pdf)\n- **[µNAS]** Constrained Neural Architecture Search for Microcontrollers |[`[pdf]`](https://dl.acm.org/doi/pdf/10.1145/3437984.3458836?utm_content=167905304\u0026utm_medium=social\u0026utm_source=linkedin\u0026hss_channel=lcp-19239958)\n- RaspberryPI for mosquito neutralization by power laser |[`[pdf]`](https://arxiv.org/pdf/2105.14190.pdf)\n- Widening Access to Applied Machine Learning with TinyML |[`[pdf]`](https://arxiv.org/pdf/2106.04008.pdf)\n- Using Machine Learning in Embedded Systems |[`[pdf]`](https://www.tiriasresearch.com/wp-content/uploads/2021/05/Using-Machine-Learning-in-Embedded-Systems.pdf)\n- **[FRILL]** A Non-Semantic Speech Embedding for Mobile Devices |[`[pdf]`](https://arxiv.org/pdf/2011.04609.pdf)\n- Few-Shot Keyword Spotting in Any Language  |[`[pdf]`](https://arxiv.org/pdf/2104.01454.pdf)\n- MLPerf Tiny Benchmark |[`[pdf]`](https://arxiv.org/pdf/2106.07597.pdf)\n- A Survey of Quantization Methods for Efficient Neural Network Inference  |[`[pdf]`](https://arxiv.org/pdf/2103.13630)\n- Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better |[`[pdf]`](https://arxiv.org/pdf/2106.08962.pdf)\n- AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge |[`[pdf]`](https://arxiv.org/pdf/2104.14623.pdf)\n- RANDOMNESS IN NEURAL NETWORK TRAINING:CHARACTERIZING THE IMPACT OF TOOLING |[`[pdf]`](https://arxiv.org/pdf/2106.11872.pdf)\n- TinyML: Analysis of Xtensa LX6 microprocessor for Neural Network Applications by ESP32 SoC |[`[pdf]`](https://arxiv.org/pdf/2106.10652.pdf)\n- **[Keyword Transformer]**: A Self-Attention Model for Keyword Spotting |[`[pdf]`](https://arxiv.org/pdf/2104.00769.pdf)\n- LB-CNN: An Open Source Framework for Fast Training of Light Binary Convolutional Neural Networks using Chainer and Cupy |[`[pdf]`](https://arxiv.org/pdf/2106.15350.pdf)\n- **[Only Train Once]**: A One-Shot Neural Network Training And Pruning Framework |[`[pdf]`](https://arxiv.org/pdf/2107.07467.pdf)\n- **[BEANNA]**: A Binary-Enabled Architecture for Neural Network Acceleration|[`[pdf]`](https://arxiv.org/pdf/2108.02313.pdf)\n- A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays |[`[pdf]`](https://arxiv.org/pdf/2110.10486.pdf)\n- CLASSIFICATION OF ANOMALOUS GAIT USING MACHINE LEARNING TECHNIQUES AND EMBEDDED SENSORS |[`[pdf]`](https://arxiv.org/pdf/2110.06139.pdf)\n- **[MOBILEVIT]**: LIGHT-WEIGHT, GENERAL-PURPOSE, AND MOBILE-FRIENDLY VISION TRANSFORMER |[`[pdf]`](https://arxiv.org/pdf/2110.02178.pdf?utm_medium=email\u0026_hsmi=175723863\u0026_hsenc=p2ANqtz--rVrB87u6eUrx_A5XM8m9kyJc-xTO-fwCZheo-n_Mx9IQ02upaLz87dMne5xsrlcFq5G0vxBHD_IzIXHOIvuR--axMLA\u0026utm_content=175723863\u0026utm_source=hs_email)\n- **[MCUNetV2]**: Memory-Efficient Patch-based Inference for Tiny Deep Learning |[`[pdf]`](https://arxiv.org/abs/2110.15352#)\n- **[LCS]**: LEARNING COMPRESSIBLE SUBSPACES FOR ADAPTIVE NETWORK COMPRESSION AT INFERENCE TIME |[`[pdf]`](https://arxiv.org/pdf/2110.04252.pdf)\n- Feature Augmented Hybrid CNN for Stress Recognition Using Wrist-based Photoplethysmography Sensor |[`[pdf]`](https://arxiv.org/pdf/2108.03166.pdf)\n- **[ANALOGNETS]**: ML-HW CO-DESIGN OF NOISE-ROBUST TINYML MODELS AND ALWAYS-ON ANALOG COMPUTE-IN-MEMORY ACCELERATOR |[`[pdf]`](https://arxiv.org/pdf/2111.06503.pdf)\n- **[BSC]**: Block-based Stochastic Computing to Enable Accurate and Efficient TinyML |[`[pdf]`](https://arxiv.org/pdf/2111.06686.pdf)\n- **[TiWS-iForest]**: Isolation Forest in Weakly Supervised and Tiny ML scenarios |[`[pdf]`](https://arxiv.org/pdf/2111.15432.pdf)\n- **[RadarNet]**: Efficient Gesture Recognition Technique Utilizing a Miniature Radar Sensor|[`[pdf]`](https://dl.acm.org/doi/pdf/10.1145/3411764.3445367)\n- The Synergy of Complex Event Processing and Tiny Machine Learning in Industrial IoT  |[`[pdf]`](https://arxiv.org/pdf/2105.03371.pdf)\n\n  | ▲ [Top](#tinyml-papers-and-projects) |\n  | ------------------------------------ |\n\n### \u003cins\u003e**2022**\u003c/ins\u003e\n\n- A Heterogeneous In-Memory Computing Cluster For Flexible End-to-End Inference of Real-World Deep Neural Networks |[`[pdf]`](https://arxiv.org/pdf/2201.01089.pdf)\n- CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAs |[`[pdf]`](https://arxiv.org/pdf/2201.01863.pdf)\n- BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing |[`[pdf]`](https://arxiv.org/pdf/2201.02693.pdf)\n- **[UDC]**: Unified DNAS for Compressible TinyML Models |[`[pdf]`](https://arxiv.org/pdf/2201.05842.pdf)\n- A VM/Containerized Approach for Scaling TinyML Applications |[`[pdf]`](https://arxiv.org/pdf/2202.05057.pdf)\n- A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spotting |[`[pdf]`](https://arxiv.org/pdf/2202.02361.pdf)\n- PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++ |[`[pdf]`](https://arxiv.org/pdf/2201.02863.pdf)\n- **[TinyMLOps]**: Operational Challenges for Widespread Edge AI Adoption |[`[pdf]`](https://arxiv.org/pdf/2203.10923.pdf)\n- **[Auritus]**: An Open-Source Optimization Toolkit for Training and Development of Human Movement Models and Filters Using Earables |[`[pdf]`](https://www.researchgate.net/publication/359759183_Auritus_An_Open-Source_Optimization_Toolkit_for_Training_and_Development_of_Human_Movement_Models_and_Filters_Using_Earables) |[`[code]`](https://github.com/nesl/auritus)\n- Enabling Hyperparameter Tuning of Machine Learning Classifiers in Production |[`[pdf]`](https://www.researchgate.net/publication/356911955_Enabling_Hyperparameter_Tuning_of_Machine_Learning_Classifiers_in_Production)\n- TinyOdom: Hardware-Aware Efficient Neural Inertial Navigation |[`[pdf]`](https://www.researchgate.net/publication/360075622_TinyOdom_Hardware-Aware_Efficient_Neural_Inertial_Navigation?fbclid=IwAR3F5LhoDiXD6tDhyE2PLFDB1hgy0IBM6V5YIUFwva7TvUvHYDi7C0ryTB8) |[`[code]`](https://github.com/nesl/tinyodom?fbclid=IwAR1zbqrymVPxsVRHT6LZOtcwjJtzUYqfd0E8ChliklUvug-D6KKhWAAZ3dg)\n- Searching for Efficient Neural Architectures for On-Device ML on Edge TPUs |[`[pdf]`](https://arxiv.org/pdf/2204.14007.pdf)\n- Green Accelerated Hoeffding Tree |[`[pdf]`](https://arxiv.org/pdf/2205.03184.pdf)\n- tinyRadar: mmWave Radar based Human Activity Classification for Edge Computing |[`[pdf]`](https://labs.dese.iisc.ac.in/neuronics/wp-content/uploads/sites/16/2022/04/mmWave_Radar_ver1.3.5.pdf)\n- MACHINE LEARNING SENSORS |[`[pdf]`](https://arxiv.org/pdf/2206.03266.pdf)\n- Evaluating Short-Term Forecasting of Multiple Time Series in IoT Environments |[`[pdf]`](https://arxiv.org/pdf/2206.07784.pdf)\n- How to train accurate BNNs for embedded systems? |[`[pdf]`](https://arxiv.org/pdf/2206.12322.pdf)\n- Vildehaye: A Family of Versatile, Widely-Applicable, and Field-Proven Lightweight Wildlife Tracking and Sensing Tags  |[`[pdf]`](https://arxiv.org/pdf/2206.06171.pdf)\n- On-Device Training Under 256KB Memory  |[`[pdf]`](https://arxiv.org/pdf/2206.15472.pdf)\n- DEPTH PRUNING WITH AUXILIARY NETWORKS FOR TINYML  |[`[pdf]`](https://arxiv.org/pdf/2204.10546.pdf)\n- **[EdgeNeXt]**: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications |[`[pdf]`](https://arxiv.org/pdf/2206.10589.pdf)\n- Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots |[`[pdf]`](https://arxiv.org/pdf/2205.05748.pdf)\n- **[POET]**: Training Neural Networks on Tiny Devices with Integrated Rematerialization and PagingPOET: Training Neural Networks on Tiny Devices |[`[pdf]`](https://arxiv.org/pdf/2207.07697.pdf)\n- Two-stage Human Activity Recognition on\nMicrocontrollers with Decision Trees and CNNs  |[`[pdf]`](https://arxiv.org/pdf/2206.07652.pdf) \n- How to Manage Tiny Machine Learning at Scale – An Industrial Perspective |[`[pdf`](https://arxiv.org/pdf/2202.09113.pdf)\n- **[SeLoC-ML]**: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoT|[`[pdf]`](https://arxiv.org/pdf/2207.08818.pdf)\n- **[IMU2Doppler]**: Cross-Modal Domain Adaptation for Doppler-based Activity Recognition Using IMU Data\" |[`[pdf]\n`](https://smashlab.io/pdfs/imu2dop.pdf)\n- **[Tiny-HR]**: Towards an interpretable machine learning\npipeline for heart rate estimation on edge devices  |[`[pdf]\n`](https://arxiv.org/pdf/2208.07981.pdf)\n- [Enabling Fast Deep Learning on Tiny Energy-Harvesting IoT Devices]|[`[pdf]`](https://arxiv.org/pdf/2111.14051.pdf)\n- Extremely Simple Activation Shaping for\nOut-of-Distribution Detection |[`[pdf]`](https://arxiv.org/pdf/2209.09858.pdf)\n- A processing‑in‑pixel‑in‑memory paradigm for resource‑constrained TinyML applications  |[`[pdf]`](https://www.nature.com/articles/s41598-022-17934-1.pdf)\n- **[tinySNN]**: Towards Memory- and Energy-Efficient Spiking Neural Networks |[`[pdf]`](https://arxiv.org/pdf/2206.08656.pdf)\n- **[DeepPicarMicro]**: Applying TinyML to Autonomous Cyber Physical Systems |[`[pdf]`](https://arxiv.org/pdf/2208.11212.pdf)\n- Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors |[`[pdf`](https://arxiv.org/pdf/2209.00591.pdf)\n-**[Protean]**: An Energy-Efficient and Heterogeneous Platform for\nAdaptive and Hardware-Accelerated Battery-free Computing |[`[pdf`](https://dl.acm.org/doi/pdf/10.1145/3560905.3568561?utm_medium=email\u0026_hsmi=249309419\u0026_hsenc=p2ANqtz--_ltviIYSpzfz9c4PiqHChBsEQkRDbr6treGEpYyBsHcwC5HX_R7JMp4ldGoydUfIlR-bOB-V2lKC0RIAhOcFen7daog\u0026utm_content=249309419\u0026utm_source=hs_email)\n- IN-SENSOR \u0026 NEUROMORPHIC COMPUTING ARE ALL YOU NEED FOR ENERGY\nEFFICIENT COMPUTER VISION  |[`[pdf]`](https://arxiv.org/pdf/2212.10881.pdf)\n- Energy Efficient Hardware Acceleration of\nNeural Networks with Power-of-Two\nQuantisation |[`[pdf]`](https://arxiv.org/pdf/2209.15257.pdf)\n- Enabling ISP-less Low-Power Computer Vision |[`[pdf]`](https://arxiv.org/pdf/2210.05451.pdf)\n- Rethinking Vision Transformers for MobileNet Size and Speed |[`[pdf]`](https://arxiv.org/pdf/2212.08059.pdf)\n- Neuromorphic Computing and Sensing in Space |[`[pdf]`](https://arxiv.org/pdf/2212.05236.pdf)\n- Joint Data Deepening-and-Prefetching for Energy-Efficient Edge Learning |[`[pdf]`](https://arxiv.org/pdf/2211.07146.pdf)\n- PreMa: Predictive Maintenance of Solenoid Valve in Real-Time at Embedded Edge-Level | [`pdf]`](https://arxiv.org/pdf/2211.12326.pdf)\n\n  | ▲ [Top](#tinyml-papers-and-projects) |\n  | ------------------------------------ |\n\n\n### \u003cins\u003e**2023**\u003c/ins\u003e\n\n- Exploring Automatic Gym Workouts Recognition Locally On Wearable Resource-Constrained Devices |[`[pdf]`](https://arxiv.org/pdf/2301.05748.pdf)\n- **[MetaLDC]**: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption |[`[pdf]`](https://arxiv.org/pdf/2302.12347.pdf)\n- Faster Attention Is What You Need: A Fast\nSelf-Attention Neural Network Backbone\nArchitecture for the Edge via Double-Condensing\nAttention Condensers |[`[pdf]`](https://arxiv.org/pdf/2208.06980.pdf)\n- **[TinyReptile]**: TinyML with Federated Meta-Learning |[`[pdf`](https://arxiv.org/pdf/2304.05201.pdf)\n- **[TinyProp]** - Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning |[`[pdf`](https://arxiv.org/pdf/2308.09201.pdf)\n\n- **[LiteTrack]** - Layer Pruning with Asynchronous Feature Extraction\nfor Lightweight and Efficient Visual Tracking - Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning |[`[pdf`](https://arxiv.org/pdf/2409.00608v1)\n\n- **[MCUFormer]** - Deploying Vision Transformers on Microcontrollers with Limited Memory |[`[pdf`](https://arxiv.org/abs/2310.16898)\n\n\n### \u003cins\u003e**2024**\u003c/ins\u003e\n\n- Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences | [`[pdf]`](https://arxiv.org/pdf/2310.04621v2)\n- TinyAgent: Function Calling at the Edge | [`[pdf]`](https://arxiv.org/pdf/2409.00608v1)\n- **[SENSORLLM]**: ALIGNING LARGE LANGUAGE MODELS WITH MOTION SENSORS FOR HUMAN ACTIVITY\nRECOGNITION | [`[pdf]`](https://arxiv.org/pdf/2410.10624)\n- **[Penetrative AI]**: Making LLMs Comprehend the Physical World | [`[pdf]`](https://arxiv.org/pdf/2310.09605v2)\n- **[MobileCLIP]**: Fast Image-Text Models through Multi-Modal Reinforced Training  | [`[pdf]`](https://arxiv.org/pdf/2311.17049)\n- **[Zero-TPrune]**: Zero-Shot Token Pruning through Leveraging of the Attention\nGraph in Pre-Trained Transformers  | [`[pdf]`](https://arxiv.org/pdf/2305.17328)\n- Towards Edge General Intelligence via Large Language Models: Opportunities and Challenges | [`[pdf]`](https://arxiv.org/pdf/2410.18125)\n\n\u003cins\u003e**2025**\u003c/ins\u003e\n- Optimizing Edge AI: A Comprehensive Survey on Data, Model, and System Strategies| [`[pdf]`](https://arxiv.org/pdf/2501.03265)\n\n  | ▲ [Top](#tinyml-papers-and-projects) |\n  | ------------------------------------ |\n\n\n## Awesome TinyML Projects\n\n### \u003cins\u003e**Projects Source code**\u003c/ins\u003e\n- TinyFederatedLearning | [`[official code]`](https://github.com/kavyakvk/TinyFederatedLearning) [`[presentation]`](https://www.youtube.com/watch?v=KSaidr3ZN9M\u0026feature=youtu.be) ![GitHub stars](https://img.shields.io/github/stars/kavyakvk/TinyFederatedLearning?style=social) \n- [TinyML Study Group](https://github.com/tinyml-team/study-group) ![GitHub stars](https://img.shields.io/github/stars/tinyml-team/study-group?style=social)\n- [Arduino trash classification TinyML example](https://github.com/lightb0x/arduino_trash_classification) ![GitHub stars](https://img.shields.io/github/stars/lightb0x/arduino_trash_classification?style=social) \n- [TinyML on Arduino](https://github.com/sandeepmistry/aimldevfest-workshop-2019) ![GitHub stars](https://img.shields.io/github/stars/sandeepmistry/aimldevfest-workshop-2019?style=social) \n- [Edge AI Anomaly Detection](https://github.com/ShawnHymel/tinyml-example-anomaly-detection) ![GitHub stars](https://img.shields.io/github/stars/ShawnHymel/tinyml-example-anomaly-detection?style=social) \n- [Air Guitar CS249R](https://github.com/RobJMal/Air-Guitar-CS249R) [`[presentation]`](https://www.youtube.com/watch?v=PVk9RUW1Hwo) ![GitHub stars](https://img.shields.io/github/stars/RobJMal/Air-Guitar-CS249R?style=social) \n- [TinyML ESP32](https://github.com/HollowMan6/TinyML-ESP32) ![GitHub stars](https://img.shields.io/github/stars/HollowMan6/TinyML-ESP32?style=social) \n- [MagicWand-TFLite-ESP32](https://github.com/andriyadi/MagicWand-TFLite-ESP32) ![GitHub stars](https://img.shields.io/github/stars/andriyadi/MagicWand-TFLite-ESP32?style=social) \n- [Localize your cat at home with BLE beacon, ESP32s, and Machine Learning](https://github.com/filipsPL/cat-localizer) ![GitHub stars](https://img.shields.io/github/stars/filipsPL/cat-localizer?style=social) \n- [ESP32 Cam and Edge Impulse](https://github.com/luisomoreau/ESP32-Cam-Edge-Impulse) ![GitHub stars](https://img.shields.io/github/stars/luisomoreau/ESP32-Cam-Edge-Impulse?style=social) \n- [The C++ Neural Network and Machine Learning project](https://github.com/intel/cppnnml) ![GitHub stars](https://img.shields.io/github/stars/intel/cppnnml?style=social) \n- [Water Meter System Complete](https://github.com/jomjol/water-meter-system-complete) ![GitHub stars](https://img.shields.io/github/stars/jomjol/water-meter-system-complete?style=social) \n- [Number recognition with MNIST on Raspberry Pi Pico](https://github.com/iwatake2222/pico-mnist) ![GitHub stars](https://img.shields.io/github/stars/iwatake2222/pico-mnist?style=social) \n- [HallSensor RPM meter using Machine Learning](https://github.com/Miguelest07/HallSensor_ML_EdgeImpulse) ![GitHub stars](https://img.shields.io/github/stars/Miguelest07/HallSensor_ML_EdgeImpulse?style=social) \n- [Weather forcasting with TinyML](https://github.com/BaptisteZloch/Weather_forcasting) ![GitHub stars](https://img.shields.io/github/stars/BaptisteZloch/Weather_forcasting?style=social) \n- [TinyML using different frameworks applied to STM32F407 uC](https://github.com/fjpolo/STM32F407TinyML) ![GitHub stars](https://img.shields.io/github/stars/fjpolo/STM32F407TinyML?style=social) \n- [CurrentSense-TinyML](https://github.com/Santandersecurityresearch/CurrentSense-TinyML) ![GitHub stars](https://img.shields.io/github/stars/Santandersecurityresearch/CurrentSense-TinyML?style=social) \n- [Tensorflow Lite for Microcontrollers in Micropython](https://github.com/mocleiri/tensorflow-micropython-examples) ![GitHub stars](https://img.shields.io/github/stars/mocleiri/tensorflow-micropython-examples?style=social) \n- [TensorFlow Lite Micro for Espressif Chipsets](https://github.com/espressif/tflite-micro-esp-examples) ![GitHub stars](https://img.shields.io/github/stars/espressif/tflite-micro-esp-examples?style=social)\n- [ML Audio Classifier Example for Pico](https://github.com/ArmDeveloperEcosystem/ml-audio-classifier-example-for-pico) ![GitHub stars](https://img.shields.io/github/stars/ArmDeveloperEcosystem/ml-audio-classifier-example-for-pico?style=social)\n- [Handwritten digit classification using Raspberry Pi Pico and Machine Learning](https://github.com/code2k13/rpipico_digit_classification)![GitHub stars](https://img.shields.io/github/stars/code2k13/rpipico_digit_classification?style=social)\n\n### \u003cins\u003e**Projects Articles**\u003c/ins\u003e\n- `2020-09` [Autonomous embedded driving using computer vision](https://www.edgeimpulse.com/blog/autonomous-driving-using-computer-vision)\n- `2020-10` [EleTect - TinyML and IoT Based Smart Wildlife Tracker](https://www.hackster.io/dhruvsheth_/eletect-tinyml-and-iot-based-smart-wildlife-tracker-c03e5a)\n- `2020-03` [Handwriting Recognition](https://www.hackster.io/naveenbskumar/handwriting-recognition-7583e3)\n- `2021-01` [Why Benchmarking TinyML Systems Is Challenging](https://analyticsindiamag.com/why-benchmarking-tinyml-systems-is-challenging/)\n- `2021-01` [Build your own Google Assistant using tinyML](https://mjrobot.org/2021/01/27/building-an-intelligent-voice-assistant-from-scratch/)\n- `2021-02` [Fall detection and heart rate monitoring using AVR-IoT](https://www.hackster.io/naveenbskumar/fall-detection-and-heart-rate-monitoring-using-avr-iot-75fb16)\n- `2021-02` [The Maker Show: TinyML for wildlife conservation](https://dev.to/fordevs-community/the-maker-show-tinyml-for-wildlife-conservation-idg)\n- `2021-05` [Under $100 and Less Than 1mW: Pneumonia Detection Solution for Everyone](https://www.edgeimpulse.com/blog/under-dollar100-and-less-than-1mw-pneumonia-detection-solution-for-everyone)\n- `2021-06` [Early Pigs' Respiratory Disease Detection Using Edge Impulse](https://www.hackster.io/clinton_oduor/early-pigs-respiratory-disease-detection-using-edge-impulse-2ab039)\n- `2021-06` [Posture Watchdog](https://www.hackster.io/naveenbskumar/posture-watchdog-c03f77?utm_campaign=Advanced%20Wearables%20Contest%20Hackster.io\u0026utm_source=twitter\u0026utm_medium=social\u0026utm_content=Dream%20Smart%20Wearables%20winner:%20posture%20watchdog)\n- `2021-07` [Localized Environmental Sensing With TinyML](https://highdemandskills.com/localized-monitoring-tinyml/)\n- `2021` [Wireless Quarter: Edge Intelligence](https://www.nordicsemi.com/-/media/Publications/Wireless-Quarter-pdf/2021/WQ_Issue_2_2021.pdf?la=en\u0026hash=A58D1AB12248E18E465658CE3CDFE33F9187692F#page=8)\n- [Arduino Machine Learning: Build a Tensorflow lite model to control robot-car](https://www.survivingwithandroid.com/arduino-machine-learning-tensorflow-lite/)\n- [TinyML ESP32-CAM: Edge Image classification with Edge Impulse](https://www.survivingwithandroid.com/tinyml-esp32-cam-edge-image-classification-with-edge-impulse/)\n- [Predictive Maintenance with TinyAutomator](https://www.waylay.io/articles/predictive-maintenance-with-tinyautomator)\n- [TinyML Person Detection with Arduino and Arducam](https://www.thetinymlbook.com/resources/tinyml-person-detection)\n\n| ▲ [Top](#tinyml-papers-and-projects) |\n| ------------------------------------ |\n\n## Benchmarking and Others\n\n- [EEMBCs EnergyRunner](https://github.com/eembc/energyrunner): The EEMBC EnergyRunner application framework for the MLPerf Tiny benchmark.\n- [MLPerf - Tiny](https://mlcommons.org/en/inference-tiny-05/): is an ML benchmark suite for extremely low-power systems such as microcontrollers. [`[GitHub]`](https://github.com/mlcommons/tiny/tree/v0.5)\n- [FedML](https://fedml.ai/): A Research Library and Benchmark for Federated Machine Learning. [`[GitHub]`](https://github.com/FedML-AI/FedML)\n- [FogML](https://github.com/tszydlo/FogML): A Research Library for source code generation of the inferencing functions for embedded devices [`[GitHub]`]()\n- [Benchmarking Machine Learning on the Edge](https://github.com/aallan/benchmarking-ml-on-the-edge)\n\n| ▲ [Top](#tinyml-papers-and-projects) |\n| ------------------------------------ |\n\n## Books\n\n- `[2022-12]` **AI at the Edge** (D. Situnayake \u0026 J. Plunkett, 2022. O'Reilly): [`[Book]`](https://www.oreilly.com/library/view/ai-at-the/9781098120191/)\n- `[2022-10]` **Machine Learning on Commodity Tiny Devices** (S. Guo \u0026 Q. Zhou, 2022. CRC Press): [`[Book]`](https://www.routledge.com/Machine-Learning-on-Commodity-Tiny-Devices-Theory-and-Practice/Guo-Zhou/p/book/9781032374239)\n- `[2022-07]` **Introduction to TinyML** (Rohit Sharma, 2022, AITS): [`[Book]`](https://www.thetinymlbook.com/) | [`[GitHub]`](https://github.com/ai-techsystems/deepC)\n- `[2022-04]` **TinyML Cookbook** (Gian Marco Iodice, 2022. Packt): [`[Book]`](https://www.packtpub.com/product/tinyml-cookbook/9781801814973) | [`[GitHub]`](https://github.com/PacktPublishing/TinyML-Cookbook)\n- `[2021-03]` **Artificial Intelligence for IoT Cookbook** (Michael Roshak, 2021. Packt): [`[Book]`](https://www.packtpub.com/product/artificial-intelligence-for-iot-cookbook/9781838981983) | [`[GitHub]`](https://github.com/PacktPublishing/Artificial-Intelligence-for-IoT-Cookbook)\n- `[2020-04]` **Mobile Deep Learning with TensorFlow Lite, ML Kit and Flutter**: Build scalable real-world projects to implement end-to-end neural networks on Android and iOS (Anubhav Singh, Rimjhim Bhadani, 2020. Packt): [`[Book]`](https://www.amazon.com/Mobile-Deep-Learning-TensorFlow-Flutter/dp/1789611210)\n- `[2020-01]` **TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers** (Pete Warden. O'Reilly Media): [`[Book]`](https://www.amazon.com/TinyML-Learning-TensorFlow-Ultra-Low-Power-Microcontrollers/dp/1492052043)\n\n| ▲ [Top](#tinyml-papers-and-projects) |\n| ------------------------------------ |\n\n## Articles\n\n- `2019-12` [TinyML as-a-Service: What is it and what does it mean for the IoT Edge?](https://www.ericsson.com/en/blog/2019/12/tinyml-as-a-service-iot-edge)\n- `2019-12` [TinyML as a Service and the challenges of machine learning at the edge](https://www.ericsson.com/en/blog/2019/12/tinyml-as-a-service)\n- `2020-05` [Model Quantization Using TensorFlow Lite](https://medium.com/sclable/model-quantization-using-tensorflow-lite-2fe6a171a90d)\n- `2020-09` [TinyML is breathing life into billions of devices](https://thenextweb.com/neural/2020/09/03/tinyml-is-breathing-life-into-billions-of-devices/)\n- `2020-12` [Predictions for Embedded Machine Learning for IoT in 2021](https://www.iotworldtoday.com/2020/12/10/predictions-for-embedded-machine-learning-for-iot-in-2021/)\n- `2020-12` [Matthew Mattina: Life-Saving Models in Your Pocket](https://read.deeplearning.ai/the-batch/issue-72/)\n- `2020-12` [Tiny four-bit computers are now all you need to train AI](https://www.technologyreview.com/2020/12/11/1014102/ai-trains-on-4-bit-computers/)\n- `2021-01` [How predictive maintenance is changing the industrial enterprise for good](https://techhq.com/2021/01/how-predictive-maintenance-is-changing-the-industrial-enterprise-for-good/)\n- `2021-02` [What is TinyML?](https://www.fierceelectronics.com/electronics/what-tinyml)\n- `2021-02` [How AI is Taking on Sensors](https://www.electropages.com/blog/2021/02/how-ai-taking-sensors)\n- `2021-04` [MLCommons™ Releases MLPerf™ Inference v1.0 Results with First Power Measurements](https://mlcommons.org/en/news/mlperf-inference-v10/)\n- `2021-05` [TapLock - A bike lock with machine learning](https://www.hackster.io/taplock/taplock-a-bike-lock-with-machine-learning-85641c)\n- `2021-05` [Taking Back Control](https://www.hackster.io/news/taking-back-control-14068dbb0bb7?fbclid=IwAR0QGucom06pzd7K5SJIdYByZr67xd29YlqTdbnK78OU7GqW540vJPeD534)\n- `2021-06` [Neural network architectures for deploying TinyML applications on commodity microcontrollers](https://community.arm.com/developer/research/b/articles/posts/neural-network-architectures-for-deploying-tinyml-applications-on-commodity-microcontrollers)\n- `2021-06` [TinyML in MicroCosmos](https://www.hackster.io/CHA_RAN/tinyml-in-microcosmos-c1161c)\n- `2021-06` [‘Small Data’ Are Also Crucial for Machine Learning](https://www.hackster.io/CHA_RAN/tinyml-in-microcosmos-c1161c)\n- `2021-07` [A natively flexible 32-bit Arm microprocessor](https://www.nature.com/articles/s41586-021-03625-w)\n- `2021-07` [Wearable Devices Can Reduce Collision Risk in Blind and Visually Impaired People](https://masseyeandear.org/news/press-releases/2021/07/wearable-devices-can-reduce-collision-risk-in-blind-and-visually-impaired-people)\n- `2021-09` [AI Inspection Using Analog Gauge as an Example](https://indatalabs.com/blog/ai-inspection)\n\n| ▲ [Top](#tinyml-papers-and-projects) |\n| ------------------------------------ |\n\n## Libraries and Tools\n\n- [Edge Impulse](https://www.edgeimpulse.com/) - Interactive platform to generate models that can run in microcontrollers. They are also quite active on social netwoks talking about recent news on EdgeAI/TinyML.\n- [EVE is Edge Virtualization Engine](https://github.com/lf-edge/eve/blob/master/README.md)\n- [microTVM](https://tvm.apache.org/docs/microtvm/index.html) - is an open source tool to optimize tensor programs.\n- [Larq](https://github.com/larq/larq) - An Open-Source Library for Training Binarized Neural Networks.\n- [Neural Network on Microcontroller (NNoM)](https://github.com/majianjia/nnom) - Higher-level layer-based Neural Network library specifically for microcontrollers. Support for CMSIS-NN.\n- [BerryNet](https://github.com/DT42/BerryNet) - Deep learning gateway on Raspberry Pi and other edge devices.\n- [Rune](https://github.com/hotg-ai/rune) - provides containers to encapsulate and deploy edgeML pipelines and applications.\n- [Onnxruntime](https://github.com/microsoft/onnxruntime) - cross-platform, high performance ML inferencing and training accelerator. \n- [deepC](https://github.com/ai-techsystems/deepC) - vendor independent TinyML deep learning library, compiler and inference framework microcomputers and micro-controllers\n- [deepC for Arduino](https://github.com/ai-techsystems/arduino) - TinyML deep learning library customized for Arduiono IDE\n- [emlearn](https://github.com/emlearn/emlearn) - Machine learning for microcontroller and embedded systems. Train in Python, then do inference on any device with a C99 compiler.\n\n| ▲ [Top](#tinyml-papers-and-projects) |\n| ------------------------------------ |\n\n## Courses\n- **11-767: On-Device Machine Learning Fall** - by CMU | [`[website]`](https://cmu-odml.github.io)\n- **TinyML4D: UNIFEI-IESTI01-TinyML-2023.1** - by UNIFEI | [`[website]`](https://github.com/Mjrovai/UNIFEI-IESTI01-TinyML-2023.1)\n- **Introduction to Embedded Deep Learning** - by CMU | [`[website]`](https://z4ziad.github.io/embed-dl-s23/EmbeddedDL_S23/)\n- **TinyML and Efficient Deep Learning** - by MIT | [`[website]`](https://efficientml.ai/)\n- **Machine Learning at the Edge on Arm: A Practical Introduction** - by  ARM | [`[edx]`](https://www.edx.org/course/machine-learning-at-the-edge-a-practical-introduction-from-arm)\n- **CS249r: Tiny Machine Learning (TinyML)** - *Harvard University* by Vijay Janapa Reddi: [sites.google.com](https://sites.google.com/g.harvard.edu/tinyml/home?authuser=0) | [`[YouTube]`](https://www.youtube.com/channel/UCLv1K6OaYHP44hXFd5rNqyA) | [`[edx]`](https://www.edx.org/professional-certificate/harvardx-tiny-machine-learning) | [`[GitHub]`](https://github.com/tinyMLx/colabs)\n- **MLOps for Scaling TinyML** - *Harvard University* by Vijay Janapa Reddi: [`[edX]`](https://www.edx.org/course/mlops-for-scaling-tinyml)\n- **Introduction to Embedded Machine Learning** - *Edge Impulse* by Shawn Hymel: [`[Coursera]`](https://www.coursera.org/learn/introduction-to-embedded-machine-learning)\n- **Embedded and Distributed AI** - *Jonkoping University, Sweden* by  Beril Sirmacek: [`[YouTube]`](https://www.youtube.com/watch?v=OTXqT00MmPA\u0026list=PLyulI6o7oOtycIT15i_I2_mhuLxnNvPvX)\n- **MLT Artificial Intelligence - EdgeAI** - Machine Learning Tokyo: [`[YouTube]`](https://www.youtube.com/playlist?list=PLaPdEEY26UXxrxn-82sqe9cTTvWC0y-rM)\n\n| ▲ [Top](#tinyml-papers-and-projects) |\n| ------------------------------------ |\n\n## TinyML Talks \u0026 Conferences\n\n- TinyML Talks, Summit \u0026 Research Symposium: [`[Website]`](https://www.tinyml.org/events) | [`[YouTube]`](https://www.youtube.com/channel/UC9iWqvsWjhowkHWVJquHwkg)\n- Embedded Vision Summit - [Edge AI \u0026 Vision Alliance](https://www.edge-ai-vision.com/): [`[Website]`](https://embeddedvisionsummit.com) | [`[YouTube]`](https://www.youtube.com/c/EdgeAIandVisionAlliance)\n- Low-Power Computer Vision Challenge (LPCV): [`[Website]`](https://lpcv.ai) | [`[YouTube]`](https://www.youtube.com/channel/UCAeAbQsRUZ8KWmGUKejtgBg)\n\n|                                                     Title                                                     |    Speaker    | Published Date |                                                  Link                                                   |\n| :-----------------------------------------------------------------------------------------------------------: | :-----------: | :------------: | :-----------------------------------------------------------------------------------------------------: |\n|           [Challenges for Large Scale Deployment of Tiny ML Devices](https://youtu.be/bwjHLrLGkOY)            |  G. Raghavan  |   2022-04-29   |            [slide](https://cms.tinyml.org/wp-content/uploads/summit2022/Raghavan-Gopal.pdf)             |\n|            [Building data-centric AI tooling for embedded engineers](https://youtu.be/9rnzM-C7QdA)            | D. Situnayake |   2022-04-29   |           [slide](https://cms.tinyml.org/wp-content/uploads/summit2022/Situnayake-Daniel.pdf)           |\n|                    [Sensors and ML: waking smarter for less](https://youtu.be/VXpQlOouBqU)                    |   A. Ataya    |   2022-05-04   |              [slide](https://cms.tinyml.org/wp-content/uploads/summit2022/Abbas-Ataya.pdf)              |\n| [MLOps for TinyML: Challenges \u0026 Directions in Operationalizing TinyML at Scale](https://youtu.be/yydnTSH0R2I) |  V.J. Reddi   |   2022-05-24   | [slide](https://cms.tinyml.org/wp-content/uploads/talks2022/tinyML_Talks_Vijay_Janapa_Reddi_220524.pdf) |\n|              [Vibration Monitoring Machine Learning Demonstration](https://youtu.be/2iInOo0Lkfs)              |  J. Edwards   |   2020-12-22   |                            [github](https://github.com/Numerix-DSP/siglib/)                             |\n|     [Moving From AI To IntelligentAI To Reduce The Cost Of AI At The Edge](https://youtu.be/mYy4Zv80tXQ)      |  J. Edwards   |   2020-12-22   |                                 [web](https://www.numerix-dsp.com/ai/)                                  |\n\n| ▲ [Top](#tinyml-papers-and-projects) |\n| ------------------------------------ |\n\n## Competitions\n- **[LPCV]**: Low-Power Computer Vision Challenge |[`[website]`](https://lpcv.ai/)\n\n\n## Other Awesome Repos\n- [Awesome Human Activity Recognition](https://github.com/Jie-su/Awesome_Human_Activity_Recognition#2-Paper-with-code)\n\n## Contact \u0026 Feedback\n\nIf you have any suggestions about TinyML papers and projects, feel free to mail me :)\n\n- [e-mail](mailto:gigwegbe@gmail.com)\n- [pull request](https://github.com/gigwegbe/tinyml-papers-and-projects/pulls)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgigwegbe%2Ftinyml-papers-and-projects","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgigwegbe%2Ftinyml-papers-and-projects","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgigwegbe%2Ftinyml-papers-and-projects/lists"}