Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/gigwegbe/tinyml-papers-and-projects

This is a list of interesting papers and projects about TinyML.
https://github.com/gigwegbe/tinyml-papers-and-projects
computer-vision embedded-systems machine-learning neural-architecture-search tinyml wake-word
Last synced: 2 months ago
JSON representation
This is a list of interesting papers and projects about TinyML.
Host: GitHub
URL: https://github.com/gigwegbe/tinyml-papers-and-projects
Owner: gigwegbe
License: mit
Created: 2020-12-24T21:06:57.000Z (about 4 years ago)
Default Branch: main
Last Pushed: 2024-10-21T22:33:19.000Z (3 months ago)
Last Synced: 2024-10-22T18:48:42.797Z (3 months ago)
Topics: computer-vision, embedded-systems, machine-learning, neural-architecture-search, tinyml, wake-word
Homepage: http://everythingml.com/
Size: 245 KB
Stars: 741
Watchers: 58
Forks: 128
Open Issues: 3
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project

edge-ai - TinyML Papers and Projects - Compilation of the most recent paper's and projects in the TinyML/EdgeAI field. (Uncategorized / Uncategorized)
awesome-emdl - TinyML Papers and Projects
StarryDivineSky - gigwegbe/tinyml-papers-and-projects
README

        ## TinyML Papers and Projects

> TinyML is awesome.

[![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)

This is a list of interesting papers, projects, articles and talks about TinyML.

- [Awesome Papers](#awesome-papers-): [2016](#2016) | [2017](#2017) | [2018](#2018) | [2019](#2019) | [2020](#2020) | [2022](#2022) | [2023](#2023) | [2024](#2024)

- [Awesome Projects](#awesome-tinyml-projects): [Projects Source code](#projects-source-code) | [Projects Articles](#projects-articles)

- [Benchmarking](#benchmarking)

- Resources

  - [Articles](#articles)

  - [Books](#books)

  - [Libraries and Tools](#libraries-and-tools)

  - [Courses](#courses)

  - [TinyML Talks](#tinyml-talks--conferences)

- [Contact & Feedback](#contact--feedback)

## Awesome Papers 

### **2016**

- DEEP COMPRESSION: COMPRESSING DEEP NEURAL NETWORKS WITH PRUNING, TRAINED QUANTIZATION AND HUFFMAN CODING | [`[pdf]`](https://arxiv.org/pdf/1510.00149.pdf)

- **[SQUEEZENET]** ALEXNET-LEVEL ACCURACY WITH50X FEWER PARAMETERS AND <0.5MB MODEL SIZE | [`[pdf]`](https://arxiv.org/pdf/1602.07360.pdf)

### **2017**

- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference | [`[pdf]`](https://arxiv.org/pdf/1712.05877.pdf)

- 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)

- ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices  | [`[pdf]`](https://www.microsoft.com/en-us/research/uploads/prod/2017/06/protonn.pdf)

- OPENMV: A PYTHON POWERED, EXTENSIBLE MACHINE VISION CAMERA | [`[pdf]`](https://arxiv.org/pdf/1711.10464.pdf) [`[official code]`]( https://github.com/openmv/openmv.git)

### **2018**

- **[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)

- Mobile Machine Learning Hardware at ARM: A Systems-on-Chip (SoC) Perspective | [`[pdf]`](https://arxiv.org/pdf/1801.06274.pdf)

- **[HAQ]** Hardware-Aware Automated Quantization with Mixed Precision | [`[pdf]`](https://arxiv.org/abs/1811.08886)

- Efficient and Robust Machine Learning for Real-World Systems | [`[pdf]`](https://arxiv.org/pdf/1812.02240.pdf)

- **[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)

- **[YOLO-LITE]** A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers | [`[pdf]`](https://arxiv.org/pdf/1811.05588v1.pdf)

- **[CMSIS-NN]** Efficient Neural Network Kernels for Arm Cortex-M CPUs | [`[pdf]`](https://arxiv.org/pdf/1801.06601.pdf)

- Quantizing deep convolutional networks for efficient inference: A whitepaper | [`[pdf]`](https://arxiv.org/pdf/1806.08342.pdf)

- **[Hello Edge]** Keyword Spotting on Microcontrollers | [`[pdf]`](https://arxiv.org/pdf/1711.07128.pdf)

  | ▲ [Top](#tinyml-papers-and-projects) |

  | --- |

### **2019**

- FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network | [`[pdf]`](https://arxiv.org/pdf/1901.02358.pdf)

- Image Classification on IoT Edge Devices: Profiling and Modeling| [`[pdf]`](https://arxiv.org/pdf/1902.11119.pdf)

- **[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)

- Energy Efficient Hardware for On-Device CNN Inference via Transfer Learning | [`[pdf]`](https://arxiv.org/pdf/1812.01672.pdf)

- Visual Wake Words Dataset | [`[pdf]`](https://arxiv.org/pdf/1906.05721.pdf)

- Compiling KB-Sized Machine Learning Models to Tiny IoT Devices | [`[pdf]`](microsoft.com/en-us/research/uploads/prod/2018/10/pldi19-SeeDot.pdf)

- Reconfigurable Multitask Audio Dynamics Processing Scheme | [`[pdf]`](https://arxiv.org/abs/1903.06392 )

- Pushing the limits of RNN Compression | [`[pdf]`](https://arxiv.org/pdf/1910.02558.pdf)

- A low-power end-to-end hybrid neuromorphic framework for surveillance applications | [`[pdf]`](https://arxiv.org/pdf/1910.09806.pdf)

- Deep Learning at the Edge | [`[pdf]`](https://arxiv.org/pdf/1910.10231.pdf)

- 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)

- **[SpArSe]** Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers  |[`[pdf]`](https://arxiv.org/pdf/1905.12107.pdf)

- **[MobileNetV2]** Inverted Residuals and Linear Bottlenecks |[`[pdf]`](https://arxiv.org/pdf/1801.04381.pdf)

- Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization  |[`[pdf]`](https://arxiv.org/pdf/1906.02107.pdf)

- Low-Power Computer Vision: Status, Challenges, Opportunities |[`[pdf]`](https://arxiv.org/pdf/1904.07714.pdf)

  | ▲ [Top](#tinyml-papers-and-projects) |

  | --- |

### **2020**

- COMPRESSING RNNS FOR IOT DEVICES BY 15-38X USING KRONECKER PRODUCTS |[`[pdf]`](https://arxiv.org/pdf/1906.02876.pdf)

- BENCHMARKING TINYML SYSTEMS: CHALLENGES AND DIRECTION |[`[pdf]`](https://arxiv.org/pdf/2003.04821v3.pdf)

- Lite Transformer with Long-Short Range Attention |[`[pdf]`](https://arxiv.org/pdf/2004.11886.pdf)

- **[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)

- **[TENSORFLOW LITE MICRO]** EMBEDDED MACHINE LEARNING ON TINYML SYSTEMS |[`[pdf]`](https://arxiv.org/pdf/2010.08678v2.pdf)

- **[AttendNets]** Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers |[`[pdf]`](https://arxiv.org/pdf/2009.14385v1.pdf)

- **[TinySpeech]** Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices |[`[pdf]`](https://arxiv.org/pdf/2008.04245v6.pdf)

- 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)

- **[MICRONETS]** NEURAL NETWORK ARCHITECTURES FOR DEPLOYING TINYML APPLICATIONS ON COMMODITY MICROCONTROLLERS |[`[pdf]`](https://arxiv.org/pdf/2010.11267v2.pdf)

- **[TinyLSTMs]** Efficient Neural Speech Enhancement for Hearing Aids |[`[pdf]`](https://arxiv.org/pdf/2005.11138.pdf)

- **[MCUNet]** Tiny Deep Learning on IoT Devices |[`[pdf]`](https://arxiv.org/abs/2007.10319) [`[official code]`](https://github.com/mit-han-lab/mcunet)

- Efficient Residue Number System Based Winograd Convolution | [`[pdf]`](https://arxiv.org/pdf/2007.12216.pdf)

- INTEGER QUANTIZATION FOR DEEP LEARNING INFERENCE: PRINCIPLES AND EMPIRICAL EVALUATION  | [`[pdf]`](https://arxiv.org/pdf/2004.09602)

- On Front-end Gain Invariant Modeling for Wake Word Spotting | [`[pdf]`](https://arxiv.org/pdf/2010.06676.pdf)

- TOWARDS DATA-EFFICIENT MODELING FOR WAKE WORD SPOTTING | [`[pdf]`](https://arxiv.org/pdf/2010.06659.pdf)

- Accurate Detection of Wake Word Start and End Using a CNN | [`[pdf]`](https://arxiv.org/pdf/2008.03790.pdf)

- **[PoPS]** Policy Pruning and Shrinking for Deep Reinforcement Learning | [`[pdf]`](https://arxiv.org/pdf/2001.05012.pdf)

- Howl: A Deployed, Open-Source Wake Word Detection System | [`[pdf]`](https://arxiv.org/pdf/2008.09606.pdf) [`[official code]`](https://github.com/castorini/howl)

- **[LeakyPick]** IoT Audio Spy Detector | [`[pdf]`](https://arxiv.org/pdf/2007.00500.pdf)

- On-Device Machine Learning: An Algorithms and Learning Theory Perspective  | [`[pdf]`](https://arxiv.org/pdf/1911.00623.pdf)

- Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers | [`[pdf]`](https://arxiv.org/pdf/2008.05124.pdf)

- OPTIMIZE WHAT MATTERS: TRAINING DNN-HMM KEYWORD SPOTTING MODEL USING END METRIC | [`[pdf]`](https://arxiv.org/pdf/2011.01151.pdf)

- **[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&_hsmi=104017359&_hsenc=p2ANqtz-_DVkWnyh_NhAV6j4hTFngepUyiNjZ5GO5CYIQfpl5NzerjwxOBQcpdkilzGpt9ic4HglvgM80h7wIkFNX89xe-3_j7Kw&utm_content=104017359&utm_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)

- **[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)

- **[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)

- A Tiny CNN Architecture for Medical Face Mask Detection for Resource-Constrained Endpoints  |[`[pdf]`](https://arxiv.org/pdf/2011.14858.pdf)

- 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&feature=youtu.be)

- **[ShadowNet]** A Secure and Efficient System for On-device Model Inference |[`[pdf]`](https://arxiv.org/pdf/2011.05905.pdf)

- Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware |[`[pdf]`](https://arxiv.org/pdf/2009.04465.pdf)

- 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)

- **[HyNNA]**: Improved Performance for Neuromorphic Vision Sensor based Surveillance

using Hybrid Neural Network Architecture |[`[pdf]`](https://arxiv.org/pdf/2003.08603.pdf)

- The Hardware Lottery |[`[pdf]`](https://arxiv.org/pdf/2009.06489.pdf)

- MLPerf Inference Benchmark |[`[pdf]`](https://arxiv.org/pdf/1911.02549.pdf)

- MLPerf Mobile Inference Benchmark : Why Mobile AI Benchmarking Is Hard and What to Do About It |[`[pdf]`](https://arxiv.org/pdf/2012.02328.pdf)

- **[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)

- 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)

- **[TinyBERT]** Distilling BERT for Natural Language Understanding  |[`[pdf]`](https://arxiv.org/pdf/1909.10351.pdf)

- **[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)

- **[FedML]** A Research Library and Benchmark for Federated Machine Learning  |[`[pdf]`](https://arxiv.org/pdf/2007.13518.pdf)

- Survey of Machine Learning Accelerators  |[`[pdf]`](https://arxiv.org/pdf/2009.00993.pdf)

  | ▲ [Top](#tinyml-papers-and-projects) |

  | --- |

### **2021**

- **[I-BERT]** Integer-only BERT Quantization |[`[pdf]`](https://arxiv.org/pdf/2101.01321.pdf)

- **[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)

- ON THE QUANTIZATION OF RECURRENT NEURAL NETWORKS |[`[pdf]`](https://arxiv.org/pdf/2101.05453.pdf)

- **[TINY TRANSDUCER]** A HIGHLY-EFFICIENT SPEECH RECOGNITION MODEL ON EDGE DEVICES |[`[pdf]`](https://arxiv.org/pdf/2101.06856.pdf)

- LARQ COMPUTE ENGINE: DESIGN, BENCHMARK, AND DEPLOY STATE-OF-THE-ART BINARIZED NEURAL NETWORKS |[`[pdf]`](https://arxiv.org/pdf/2011.09398.pdf)

- **[LEAF]** A LEARNABLE FRONTEND FOR AUDIO CLASSIFICATION |[`[pdf]`](https://arxiv.org/pdf/2101.08596.pdf)

- Enabling Large NNs on Tiny MCUs with Swapping |[`[pdf]`](https://arxiv.org/pdf/2101.08744.pdf)

- Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms |[`[pdf]`](https://arxiv.org/pdf/2102.02147.pdf)

- Estimating indoor occupancy through low-cost BLE devices |[`[pdf]`](https://arxiv.org/pdf/2102.03351.pdf)

- **[Tiny Eats]** Eating Detection on a Microcontroller |[`[pdf]`](https://arxiv.org/pdf/2003.06699.pdf)

- **[DEVICETTS]** A SMALL-FOOTPRINT, FAST, STABLE NETWORK FOR ON-DEVICE TEXT-TO-SPEECH |[`[pdf]`](https://arxiv.org/pdf/2010.15311.pdf)

- A 0.57-GOPS/DSP Object Detection PIM Accelerator on FPGA |[`[pdf]`](https://dl.acm.org/doi/pdf/10.1145/3394885.3431659)

- Rethinking Co-design of Neural Architectures and Hardware Accelerators |[`[pdf]`](https://arxiv.org/pdf/2102.08619.pdf)

- Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks |[`[pdf]`](https://arxiv.org/pdf/2102.00554.pdf)

- **[Apollo]** Transferable Architecture Exploration |[`[pdf]`](https://arxiv.org/pdf/2102.01723.pdf)

- DEEP NEURAL NETWORK BASED COUGH DETECTION USING BED-MOUNTED ACCELEROMETER MEASUREMENTS |[`[pdf]`](https://arxiv.org/pdf/2102.04997.pdf)

- 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)

- MEMORY-EFFICIENT SPEECH RECOGNITION ON SMART DEVICES |[`[pdf]`](https://arxiv.org/pdf/2102.11531.pdf)

- SWIS - Shared Weight bIt Sparsity for Efficient Neural Network Acceleration |[`[pdf]`](https://arxiv.org/pdf/2103.01308.pdf)

- Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware |[`[pdf]`](https://arxiv.org/pdf/2009.04465.pdf)

- Hypervector Design for Efficient Hyperdimensional Computing on Edge Devices  |[`[pdf]`](https://arxiv.org/pdf/2103.06709.pdf)

- When Being Soft Makes You Tough:A Collision Resilient Quadcopter Inspired by Arthropod Exoskeletons |[`[pdf]`](https://arxiv.org/pdf/2103.04423.pdf)

- **[TinyOL]** TinyML with Online-Learning on Microcontrollers |[`[pdf]`](https://arxiv.org/pdf/2103.08295.pdf)

- Quantization-Guided Training for Compact TinyML Models |[`[pdf]`](https://arxiv.org/pdf/2103.06231.pdf)

- hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices |[`[pdf]`](https://arxiv.org/pdf/2103.05579.pdf)

- Memory-Efficient, Limb Position-Aware Hand Gesture Recognition using Hyperdimensional Computing |[`[pdf]`](https://arxiv.org/pdf/2103.05267.pdf)

- Dynamically Throttleable Neural Networks(TNN) |[`[pdf]`](https://arxiv.org/pdf/2011.02836.pdf)

- A Comprehensive Survey on Hardware-Aware Neural Architecture Search |[`[pdf]`](https://arxiv.org/pdf/2101.09336.pdf)

- An Intelligent Bed Sensor System for Non-Contact Respiratory Rate Monitoring |[`[pdf]`](https://arxiv.org/pdf/2103.13792.pdf)

- Measuring what Really Matters: Optimizing Neural Networks for TinyML |[`[pdf]`](https://arxiv.org/pdf/2104.10645.pdf)

- Few-Shot Keyword Spotting in Any Language |[`[pdf]`](https://arxiv.org/pdf/2104.01454.pdf)

- 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)

- **[OutlierNets]** Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection |[`[pdf]`](https://arxiv.org/pdf/2104.00528.pdf)

- **[TENT]** Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT |[`[pdf]`](https://arxiv.org/pdf/2104.02233.pdf)

- A 1D-CNN Based Deep Learning Technique for Sleep Apnea Detection in IoT Sensors  |[`[pdf]`](https://arxiv.org/pdf/2105.00528.pdf)

- ADAPTIVE TEST-TIME AUGMENTATION FOR LOW-POWER CPU |[`[pdf]`](https://arxiv.org/pdf/2105.06183.pdf)

- Compiler Toolchains for Deep Learning Workloads on Embedded Platforms |[`[pdf]`](https://arxiv.org/pdf/2104.04576.pdf)

- **[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)

- **[Fusion-DHL]** WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments |[`[pdf]`](https://arxiv.org/pdf/2105.08837.pdf)

- **[µNAS]** Constrained Neural Architecture Search for Microcontrollers |[`[pdf]`](https://dl.acm.org/doi/pdf/10.1145/3437984.3458836?utm_content=167905304&utm_medium=social&utm_source=linkedin&hss_channel=lcp-19239958)

- RaspberryPI for mosquito neutralization by power laser |[`[pdf]`](https://arxiv.org/pdf/2105.14190.pdf)

- Widening Access to Applied Machine Learning with TinyML |[`[pdf]`](https://arxiv.org/pdf/2106.04008.pdf)

- Using Machine Learning in Embedded Systems |[`[pdf]`](https://www.tiriasresearch.com/wp-content/uploads/2021/05/Using-Machine-Learning-in-Embedded-Systems.pdf)

- **[FRILL]** A Non-Semantic Speech Embedding for Mobile Devices |[`[pdf]`](https://arxiv.org/pdf/2011.04609.pdf)

- Few-Shot Keyword Spotting in Any Language  |[`[pdf]`](https://arxiv.org/pdf/2104.01454.pdf)

- MLPerf Tiny Benchmark |[`[pdf]`](https://arxiv.org/pdf/2106.07597.pdf)

- A Survey of Quantization Methods for Efficient Neural Network Inference  |[`[pdf]`](https://arxiv.org/pdf/2103.13630)

- Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better |[`[pdf]`](https://arxiv.org/pdf/2106.08962.pdf)

- AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge |[`[pdf]`](https://arxiv.org/pdf/2104.14623.pdf)

- RANDOMNESS IN NEURAL NETWORK TRAINING:CHARACTERIZING THE IMPACT OF TOOLING |[`[pdf]`](https://arxiv.org/pdf/2106.11872.pdf)

- TinyML: Analysis of Xtensa LX6 microprocessor for Neural Network Applications by ESP32 SoC |[`[pdf]`](https://arxiv.org/pdf/2106.10652.pdf)

- **[Keyword Transformer]**: A Self-Attention Model for Keyword Spotting |[`[pdf]`](https://arxiv.org/pdf/2104.00769.pdf)

- 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)

- **[Only Train Once]**: A One-Shot Neural Network Training And Pruning Framework |[`[pdf]`](https://arxiv.org/pdf/2107.07467.pdf)

- **[BEANNA]**: A Binary-Enabled Architecture for Neural Network Acceleration|[`[pdf]`](https://arxiv.org/pdf/2108.02313.pdf)

- A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays |[`[pdf]`](https://arxiv.org/pdf/2110.10486.pdf)

- CLASSIFICATION OF ANOMALOUS GAIT USING MACHINE LEARNING TECHNIQUES AND EMBEDDED SENSORS |[`[pdf]`](https://arxiv.org/pdf/2110.06139.pdf)

- **[MOBILEVIT]**: LIGHT-WEIGHT, GENERAL-PURPOSE, AND MOBILE-FRIENDLY VISION TRANSFORMER |[`[pdf]`](https://arxiv.org/pdf/2110.02178.pdf?utm_medium=email&_hsmi=175723863&_hsenc=p2ANqtz--rVrB87u6eUrx_A5XM8m9kyJc-xTO-fwCZheo-n_Mx9IQ02upaLz87dMne5xsrlcFq5G0vxBHD_IzIXHOIvuR--axMLA&utm_content=175723863&utm_source=hs_email)

- **[MCUNetV2]**: Memory-Efficient Patch-based Inference for Tiny Deep Learning |[`[pdf]`](https://arxiv.org/abs/2110.15352#)

- **[LCS]**: LEARNING COMPRESSIBLE SUBSPACES FOR ADAPTIVE NETWORK COMPRESSION AT INFERENCE TIME |[`[pdf]`](https://arxiv.org/pdf/2110.04252.pdf)

- Feature Augmented Hybrid CNN for Stress Recognition Using Wrist-based Photoplethysmography Sensor |[`[pdf]`](https://arxiv.org/pdf/2108.03166.pdf)

- **[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)

- **[BSC]**: Block-based Stochastic Computing to Enable Accurate and Efficient TinyML |[`[pdf]`](https://arxiv.org/pdf/2111.06686.pdf)

- **[TiWS-iForest]**: Isolation Forest in Weakly Supervised and Tiny ML scenarios |[`[pdf]`](https://arxiv.org/pdf/2111.15432.pdf)

- **[RadarNet]**: Efficient Gesture Recognition Technique Utilizing a Miniature Radar Sensor|[`[pdf]`](https://dl.acm.org/doi/pdf/10.1145/3411764.3445367)

- The Synergy of Complex Event Processing and Tiny Machine Learning in Industrial IoT  |[`[pdf]`](https://arxiv.org/pdf/2105.03371.pdf)

  | ▲ [Top](#tinyml-papers-and-projects) |

  | --- |

### **2022**

- 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)

- CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAs |[`[pdf]`](https://arxiv.org/pdf/2201.01863.pdf)

- BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing |[`[pdf]`](https://arxiv.org/pdf/2201.02693.pdf)

- **[UDC]**: Unified DNAS for Compressible TinyML Models |[`[pdf]`](https://arxiv.org/pdf/2201.05842.pdf)

- A VM/Containerized Approach for Scaling TinyML Applications |[`[pdf]`](https://arxiv.org/pdf/2202.05057.pdf)

- A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spotting |[`[pdf]`](https://arxiv.org/pdf/2202.02361.pdf)

- 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)

- **[TinyMLOps]**: Operational Challenges for Widespread Edge AI Adoption |[`[pdf]`](https://arxiv.org/pdf/2203.10923.pdf)

- **[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)

- 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)

- 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)

- Searching for Efficient Neural Architectures for On-Device ML on Edge TPUs |[`[pdf]`](https://arxiv.org/pdf/2204.14007.pdf)

- Green Accelerated Hoeffding Tree |[`[pdf]`](https://arxiv.org/pdf/2205.03184.pdf)

- 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)

- MACHINE LEARNING SENSORS |[`[pdf]`](https://arxiv.org/pdf/2206.03266.pdf)

- Evaluating Short-Term Forecasting of Multiple Time Series in IoT Environments |[`[pdf]`](https://arxiv.org/pdf/2206.07784.pdf)

- How to train accurate BNNs for embedded systems? |[`[pdf]`](https://arxiv.org/pdf/2206.12322.pdf)

- Vildehaye: A Family of Versatile, Widely-Applicable, and Field-Proven Lightweight Wildlife Tracking and Sensing Tags  |[`[pdf]`](https://arxiv.org/pdf/2206.06171.pdf)

- On-Device Training Under 256KB Memory  |[`[pdf]`](https://arxiv.org/pdf/2206.15472.pdf)

- DEPTH PRUNING WITH AUXILIARY NETWORKS FOR TINYML  |[`[pdf]`](https://arxiv.org/pdf/2204.10546.pdf)

- **[EdgeNeXt]**: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications |[`[pdf]`](https://arxiv.org/pdf/2206.10589.pdf)

- Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots |[`[pdf]`](https://arxiv.org/pdf/2205.05748.pdf)

- **[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)

- Two-stage Human Activity Recognition on

Microcontrollers with Decision Trees and CNNs  |[`[pdf]`](https://arxiv.org/pdf/2206.07652.pdf) 

- How to Manage Tiny Machine Learning at Scale – An Industrial Perspective |[`[pdf`](https://arxiv.org/pdf/2202.09113.pdf)

- **[SeLoC-ML]**: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoT|[`[pdf]`](https://arxiv.org/pdf/2207.08818.pdf)

- **[IMU2Doppler]**: Cross-Modal Domain Adaptation for Doppler-based Activity Recognition Using IMU Data" |[`[pdf]

`](https://smashlab.io/pdfs/imu2dop.pdf)

- **[Tiny-HR]**: Towards an interpretable machine learning

pipeline for heart rate estimation on edge devices  |[`[pdf]

`](https://arxiv.org/pdf/2208.07981.pdf)

- [Enabling Fast Deep Learning on Tiny Energy-Harvesting IoT Devices]|[`[pdf]`](https://arxiv.org/pdf/2111.14051.pdf)

- Extremely Simple Activation Shaping for

Out-of-Distribution Detection |[`[pdf]`](https://arxiv.org/pdf/2209.09858.pdf)

- A processing‑in‑pixel‑in‑memory paradigm for resource‑constrained TinyML applications  |[`[pdf]`](https://www.nature.com/articles/s41598-022-17934-1.pdf)

- **[tinySNN]**: Towards Memory- and Energy-Efficient Spiking Neural Networks |[`[pdf]`](https://arxiv.org/pdf/2206.08656.pdf)

- **[DeepPicarMicro]**: Applying TinyML to Autonomous Cyber Physical Systems |[`[pdf]`](https://arxiv.org/pdf/2208.11212.pdf)

- Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors |[`[pdf`](https://arxiv.org/pdf/2209.00591.pdf)

-**[Protean]**: An Energy-Efficient and Heterogeneous Platform for

Adaptive and Hardware-Accelerated Battery-free Computing |[`[pdf`](https://dl.acm.org/doi/pdf/10.1145/3560905.3568561?utm_medium=email&_hsmi=249309419&_hsenc=p2ANqtz--_ltviIYSpzfz9c4PiqHChBsEQkRDbr6treGEpYyBsHcwC5HX_R7JMp4ldGoydUfIlR-bOB-V2lKC0RIAhOcFen7daog&utm_content=249309419&utm_source=hs_email)

- IN-SENSOR & NEUROMORPHIC COMPUTING ARE ALL YOU NEED FOR ENERGY

EFFICIENT COMPUTER VISION  |[`[pdf]`](https://arxiv.org/pdf/2212.10881.pdf)

- Energy Efficient Hardware Acceleration of

Neural Networks with Power-of-Two

Quantisation |[`[pdf]`](https://arxiv.org/pdf/2209.15257.pdf)

- Enabling ISP-less Low-Power Computer Vision |[`[pdf]`](https://arxiv.org/pdf/2210.05451.pdf)

- Rethinking Vision Transformers for MobileNet Size and Speed |[`[pdf]`](https://arxiv.org/pdf/2212.08059.pdf)

- Neuromorphic Computing and Sensing in Space |[`[pdf]`](https://arxiv.org/pdf/2212.05236.pdf)

- Joint Data Deepening-and-Prefetching for Energy-Efficient Edge Learning |[`[pdf]`](https://arxiv.org/pdf/2211.07146.pdf)

- PreMa: Predictive Maintenance of Solenoid Valve in Real-Time at Embedded Edge-Level | [`pdf]`](https://arxiv.org/pdf/2211.12326.pdf)

  | ▲ [Top](#tinyml-papers-and-projects) |

  | --- |

### **2023**

- Exploring Automatic Gym Workouts Recognition Locally On Wearable Resource-Constrained Devices |[`[pdf]`](https://arxiv.org/pdf/2301.05748.pdf)

- **[MetaLDC]**: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption |[`[pdf]`](https://arxiv.org/pdf/2302.12347.pdf)

- Faster Attention Is What You Need: A Fast

Self-Attention Neural Network Backbone

Architecture for the Edge via Double-Condensing

Attention Condensers |[`[pdf]`](https://arxiv.org/pdf/2208.06980.pdf)

- **[TinyReptile]**: TinyML with Federated Meta-Learning |[`[pdf`](https://arxiv.org/pdf/2304.05201.pdf)

- **[TinyProp]** - Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning |[`[pdf`](https://arxiv.org/pdf/2308.09201.pdf)

- **[LiteTrack]** - Layer Pruning with Asynchronous Feature Extraction

for Lightweight and Efficient Visual Tracking - Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning |[`[pdf`](https://arxiv.org/pdf/2409.00608v1)

- **[MCUFormer]** - Deploying Vision Transformers on Microcontrollers with Limited Memory |[`[pdf`](https://arxiv.org/abs/2310.16898)

### **2024**

- Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences | [`[pdf]`](https://arxiv.org/pdf/2310.04621v2)

- TinyAgent: Function Calling at the Edge | [`[pdf]`](https://arxiv.org/pdf/2409.00608v1)

- **[SENSORLLM]**: ALIGNING LARGE LANGUAGE MODELS WITH MOTION SENSORS FOR HUMAN ACTIVITY

RECOGNITION | [`[pdf]`](https://arxiv.org/pdf/2410.10624)

- **[Penetrative AI]**: Making LLMs Comprehend the Physical World | [`[pdf]`](https://arxiv.org/pdf/2310.09605v2)

- **[MobileCLIP]**: Fast Image-Text Models through Multi-Modal Reinforced Training  | [`[pdf]`](https://arxiv.org/pdf/2311.17049)

- **[Zero-TPrune]**: Zero-Shot Token Pruning through Leveraging of the Attention

Graph in Pre-Trained Transformers  | [`[pdf]`](https://arxiv.org/pdf/2305.17328)

  | ▲ [Top](#tinyml-papers-and-projects) |

  | --- |

## Awesome TinyML Projects

### **Projects Source code**

- TinyFederatedLearning | [`[official code]`](https://github.com/kavyakvk/TinyFederatedLearning) [`[presentation]`](https://www.youtube.com/watch?v=KSaidr3ZN9M&feature=youtu.be) ![GitHub stars](https://img.shields.io/github/stars/kavyakvk/TinyFederatedLearning?style=social) 

- [TinyML Study Group](https://github.com/tinyml-team/study-group) ![GitHub stars](https://img.shields.io/github/stars/tinyml-team/study-group?style=social)

- [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) 

- [TinyML on Arduino](https://github.com/sandeepmistry/aimldevfest-workshop-2019) ![GitHub stars](https://img.shields.io/github/stars/sandeepmistry/aimldevfest-workshop-2019?style=social) 

- [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) 

- [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) 

- [TinyML ESP32](https://github.com/HollowMan6/TinyML-ESP32) ![GitHub stars](https://img.shields.io/github/stars/HollowMan6/TinyML-ESP32?style=social) 

- [MagicWand-TFLite-ESP32](https://github.com/andriyadi/MagicWand-TFLite-ESP32) ![GitHub stars](https://img.shields.io/github/stars/andriyadi/MagicWand-TFLite-ESP32?style=social) 

- [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) 

- [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) 

- [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) 

- [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) 

- [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) 

- [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) 

- [Weather forcasting with TinyML](https://github.com/BaptisteZloch/Weather_forcasting) ![GitHub stars](https://img.shields.io/github/stars/BaptisteZloch/Weather_forcasting?style=social) 

- [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) 

- [CurrentSense-TinyML](https://github.com/Santandersecurityresearch/CurrentSense-TinyML) ![GitHub stars](https://img.shields.io/github/stars/Santandersecurityresearch/CurrentSense-TinyML?style=social) 

- [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) 

- [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)

- [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)

- [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)

### **Projects Articles**

- `2020-09` [Autonomous embedded driving using computer vision](https://www.edgeimpulse.com/blog/autonomous-driving-using-computer-vision)

- `2020-10` [EleTect - TinyML and IoT Based Smart Wildlife Tracker](https://www.hackster.io/dhruvsheth_/eletect-tinyml-and-iot-based-smart-wildlife-tracker-c03e5a)

- `2020-03` [Handwriting Recognition](https://www.hackster.io/naveenbskumar/handwriting-recognition-7583e3)

- `2021-01` [Why Benchmarking TinyML Systems Is Challenging](https://analyticsindiamag.com/why-benchmarking-tinyml-systems-is-challenging/)

- `2021-01` [Build your own Google Assistant using tinyML](https://mjrobot.org/2021/01/27/building-an-intelligent-voice-assistant-from-scratch/)

- `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)

- `2021-02` [The Maker Show: TinyML for wildlife conservation](https://dev.to/fordevs-community/the-maker-show-tinyml-for-wildlife-conservation-idg)

- `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)

- `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)

- `2021-06` [Posture Watchdog](https://www.hackster.io/naveenbskumar/posture-watchdog-c03f77?utm_campaign=Advanced%20Wearables%20Contest%20Hackster.io&utm_source=twitter&utm_medium=social&utm_content=Dream%20Smart%20Wearables%20winner:%20posture%20watchdog)

- `2021-07` [Localized Environmental Sensing With TinyML](https://highdemandskills.com/localized-monitoring-tinyml/)

- `2021` [Wireless Quarter: Edge Intelligence](https://www.nordicsemi.com/-/media/Publications/Wireless-Quarter-pdf/2021/WQ_Issue_2_2021.pdf?la=en&hash=A58D1AB12248E18E465658CE3CDFE33F9187692F#page=8)

- [Arduino Machine Learning: Build a Tensorflow lite model to control robot-car](https://www.survivingwithandroid.com/arduino-machine-learning-tensorflow-lite/)

- [TinyML ESP32-CAM: Edge Image classification with Edge Impulse](https://www.survivingwithandroid.com/tinyml-esp32-cam-edge-image-classification-with-edge-impulse/)

- [Predictive Maintenance with TinyAutomator](https://www.waylay.io/articles/predictive-maintenance-with-tinyautomator)

- [TinyML Person Detection with Arduino and Arducam](https://www.thetinymlbook.com/resources/tinyml-person-detection)

| ▲ [Top](#tinyml-papers-and-projects) |

| --- |

## Benchmarking and Others

- [EEMBCs EnergyRunner](https://github.com/eembc/energyrunner): The EEMBC EnergyRunner application framework for the MLPerf Tiny benchmark.

- [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)

- [FedML](https://fedml.ai/): A Research Library and Benchmark for Federated Machine Learning. [`[GitHub]`](https://github.com/FedML-AI/FedML)

- [FogML](https://github.com/tszydlo/FogML): A Research Library for source code generation of the inferencing functions for embedded devices [`[GitHub]`]()

- [Benchmarking Machine Learning on the Edge](https://github.com/aallan/benchmarking-ml-on-the-edge)

| ▲ [Top](#tinyml-papers-and-projects) |

| --- |

## Books

- `[2022-12]` **AI at the Edge** (D. Situnayake & J. Plunkett, 2022. O'Reilly): [`[Book]`](https://www.oreilly.com/library/view/ai-at-the/9781098120191/)

- `[2022-10]` **Machine Learning on Commodity Tiny Devices** (S. Guo & Q. Zhou, 2022. CRC Press): [`[Book]`](https://www.routledge.com/Machine-Learning-on-Commodity-Tiny-Devices-Theory-and-Practice/Guo-Zhou/p/book/9781032374239)

- `[2022-07]` **Introduction to TinyML** (Rohit Sharma, 2022, AITS): [`[Book]`](https://www.thetinymlbook.com/) | [`[GitHub]`](https://github.com/ai-techsystems/deepC)

- `[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)

- `[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)

- `[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)

- `[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)

| ▲ [Top](#tinyml-papers-and-projects) |

| --- |

## Articles

- `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)

- `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)

- `2020-05` [Model Quantization Using TensorFlow Lite](https://medium.com/sclable/model-quantization-using-tensorflow-lite-2fe6a171a90d)

- `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/)

- `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/)

- `2020-12` [Matthew Mattina: Life-Saving Models in Your Pocket](https://read.deeplearning.ai/the-batch/issue-72/)

- `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/)

- `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/)

- `2021-02` [What is TinyML?](https://www.fierceelectronics.com/electronics/what-tinyml)

- `2021-02` [How AI is Taking on Sensors](https://www.electropages.com/blog/2021/02/how-ai-taking-sensors)

- `2021-04` [MLCommons™ Releases MLPerf™ Inference v1.0 Results with First Power Measurements](https://mlcommons.org/en/news/mlperf-inference-v10/)

- `2021-05` [TapLock - A bike lock with machine learning](https://www.hackster.io/taplock/taplock-a-bike-lock-with-machine-learning-85641c)

- `2021-05` [Taking Back Control](https://www.hackster.io/news/taking-back-control-14068dbb0bb7?fbclid=IwAR0QGucom06pzd7K5SJIdYByZr67xd29YlqTdbnK78OU7GqW540vJPeD534)

- `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)

- `2021-06` [TinyML in MicroCosmos](https://www.hackster.io/CHA_RAN/tinyml-in-microcosmos-c1161c)

- `2021-06` [‘Small Data’ Are Also Crucial for Machine Learning](https://www.hackster.io/CHA_RAN/tinyml-in-microcosmos-c1161c)

- `2021-07` [A natively flexible 32-bit Arm microprocessor](https://www.nature.com/articles/s41586-021-03625-w)

- `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)

- `2021-09` [AI Inspection Using Analog Gauge as an Example](https://indatalabs.com/blog/ai-inspection)

| ▲ [Top](#tinyml-papers-and-projects) |

| --- |

## Libraries and Tools

- [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.

- [EVE is Edge Virtualization Engine](https://github.com/lf-edge/eve/blob/master/README.md)

- [microTVM](https://tvm.apache.org/docs/microtvm/index.html) - is an open source tool to optimize tensor programs.

- [Larq](https://github.com/larq/larq) - An Open-Source Library for Training Binarized Neural Networks.

- [Neural Network on Microcontroller (NNoM)](https://github.com/majianjia/nnom) - Higher-level layer-based Neural Network library specifically for microcontrollers. Support for CMSIS-NN.

- [BerryNet](https://github.com/DT42/BerryNet) - Deep learning gateway on Raspberry Pi and other edge devices.

- [Rune](https://github.com/hotg-ai/rune) - provides containers to encapsulate and deploy edgeML pipelines and applications.

- [Onnxruntime](https://github.com/microsoft/onnxruntime) - cross-platform, high performance ML inferencing and training accelerator. 

- [deepC](https://github.com/ai-techsystems/deepC) - vendor independent TinyML deep learning library, compiler and inference framework microcomputers and micro-controllers

- [deepC for Arduino](https://github.com/ai-techsystems/arduino) - TinyML deep learning library customized for Arduiono IDE

- [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.

| ▲ [Top](#tinyml-papers-and-projects) |

| --- |

## Courses

- **11-767: On-Device Machine Learning Fall** - by CMU | [`[website]`](https://cmu-odml.github.io)

- **TinyML4D: UNIFEI-IESTI01-TinyML-2023.1** - by UNIFEI | [`[website]`](https://github.com/Mjrovai/UNIFEI-IESTI01-TinyML-2023.1)

- **Introduction to Embedded Deep Learning** - by CMU | [`[website]`](https://z4ziad.github.io/embed-dl-s23/EmbeddedDL_S23/)

- **TinyML and Efficient Deep Learning** - by MIT | [`[website]`](https://efficientml.ai/)

- **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)

- **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)

- **MLOps for Scaling TinyML** - *Harvard University* by Vijay Janapa Reddi: [`[edX]`](https://www.edx.org/course/mlops-for-scaling-tinyml)

- **Introduction to Embedded Machine Learning** - *Edge Impulse* by Shawn Hymel: [`[Coursera]`](https://www.coursera.org/learn/introduction-to-embedded-machine-learning)

- **Embedded and Distributed AI** - *Jonkoping University, Sweden* by  Beril Sirmacek: [`[YouTube]`](https://www.youtube.com/watch?v=OTXqT00MmPA&list=PLyulI6o7oOtycIT15i_I2_mhuLxnNvPvX)

- **MLT Artificial Intelligence - EdgeAI** - Machine Learning Tokyo: [`[YouTube]`](https://www.youtube.com/playlist?list=PLaPdEEY26UXxrxn-82sqe9cTTvWC0y-rM)

| ▲ [Top](#tinyml-papers-and-projects) |

| --- |

## TinyML Talks & Conferences

- TinyML Talks, Summit & Research Symposium: [`[Website]`](https://www.tinyml.org/events) | [`[YouTube]`](https://www.youtube.com/channel/UC9iWqvsWjhowkHWVJquHwkg)

- Embedded Vision Summit - [Edge AI & Vision Alliance](https://www.edge-ai-vision.com/): [`[Website]`](https://embeddedvisionsummit.com) | [`[YouTube]`](https://www.youtube.com/c/EdgeAIandVisionAlliance)

- Low-Power Computer Vision Challenge (LPCV): [`[Website]`](https://lpcv.ai) | [`[YouTube]`](https://www.youtube.com/channel/UCAeAbQsRUZ8KWmGUKejtgBg)

|  Title       |                     Speaker               |       Published Date      |            Link           |

|:------------:|:-----------------------------------------:|:-------------------------:|:-------------------------:|

| [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) |

| [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) |

| [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) |

| [MLOps for TinyML: Challenges & 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) |

| [Vibration Monitoring Machine Learning Demonstration](https://youtu.be/2iInOo0Lkfs) | J. Edwards | 2020-12-22 | [github](https://github.com/Numerix-DSP/siglib/) |

| [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/) |

| ▲ [Top](#tinyml-papers-and-projects) |

| --- |

## Competitions

- **[LPCV]**: Low-Power Computer Vision Challenge |[`[website]`](https://lpcv.ai/)

## Other Awesome Repos

- [Awesome Human Activity Recognition](https://github.com/Jie-su/Awesome_Human_Activity_Recognition#2-Paper-with-code)

## Contact & Feedback

If you have any suggestions about TinyML papers and projects, feel free to mail me :)

- [e-mail](mailto:[email protected])

- [pull request](https://github.com/gigwegbe/tinyml-papers-and-projects/pulls)