Note: each student is required to choose 1 paper from this list and present in class (presentation schedule TBD). Students are NOT expected to read all papers in this list — only papers selected by student presenters will be discussed (typically 3 papers per class).
Please use this Google Sheet to sign up for your choice of paper.
Core Ideas
- 1.[Howard 2017]
Google AI
Mobilenets: Efficient convolutional neural networks for mobile vision applications
Arxiv - 2.[Sandler 2018]
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. - 3.[Zhang 2017]
Megvii
Shufflenet: An extremely efficient convolutional neural network for mobile devices
Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. - 4.[Ma 2018]
Megvii
Shufflenet v2: Practical guidelines for efficient cnn architecture design
Proceedings of the European conference on computer vision (ECCV). 2018. - 5.[Hubara 2018]
Quantized neural networks: Training neural networks with low precision weights and activations
Journal of Machine Learning Research, 2018 - 6.[Jain 2020]
Efficient Execution of Quantized Deep Learning Models: A Compiler Approach - 7.[Guo 2018]
A survey on methods and theories of quantized neural networks
Arxiv - 8.[Bonawitz 2019]
Towards federated learning at scale: System design
Programming Languages
- 9.[David 2020]
Tensorflow lite micro: Embedded machine learning on tinyml systems
Arxiv
Tools
- 10.[Chen 2018]
TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
OSDI,18 - 11.[Banbury 2021]
Micronets: Neural network architectures for deploying tinyml applications on commodity microcontrollers
Proceedings of the 4th MLSys Conference - 12.[Cyphers 2018]
Intel ngraph: An intermediate representation, compiler, and executor for deep learning
Arxiv - 13.[Chen 2020]
Experiments and optimizations for TVM on RISC-V Architectures with P Extension - 14.[Lugaresi 2019]
MediaPipe: A Framework for Building Perception Pipelines - 15.[Jiang 2020]
Mnn: A universal and efficient inference engine
Platforms
- 16.[Wang 2019 Bench]
Benchmarking TPU, GPU, and CPU Platforms for Deep Learning - 17.[Yazdanbakhsh 2021]
An evaluation of edge tpu accelerators for convolutional neural networks - 18.[Reuther 2019]
Survey and benchmarking of machine learning accelerators
HPEC, IEEE, 2019 - 19.[Osman 2021]
TinyML Platforms Benchmarking - 20. [Dong 2022]
TinyNet: a lightweight, modular, and unified network architecture for the internet of things
ACM MobiSys’22
Applications in Embedded AI
- 21.[Metwaly 2019]
Edge Computing with Embedded AI: Thermal Image Analysis for Occupancy Estimation in Intelligent Buildings
Proceedings of the INTelligent Embedded Systems Architectures and Applications Workshop 2019 - 22.[Mazzia 2020]
Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application
IEEE Access 8 (2020): 9102-9114. - 23.[Wang 2019 In-Edge]
In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning
IEEE Network 33.5 (2019): 156-165. - 24.[Zhang 2020]
Mediapipe hands: On-device real-time hand tracking - 25.[Castro-Zunti 2020]
License plate segmentation and recognition system using deep learning and OpenVINO
IET Intelligent Transport Systems 14.2 (2020): 119-126. - 26.[Xu 2019]
A First Look at Deep Learning Apps on Smartphones
The World Wide Web Conference. 2019. - 27.[Rahman 2021]
An Internet-of-Medical-Things-Enabled Edge Computing Framework for Tackling COVID-19
IEEE Internet of Things Journal 8.21 (2021): 15847-15854. - 28.[Nahian 2020]
Towards Artificial Intelligence Driven Emotion Aware Fall Monitoring Framework Suitable for Elderly People with Neurological Disorder
International Conference on Brain Informatics. Springer, Cham, 2020. - 29.[Lin 2021]
Intelligent warehouse monitoring based on distributed system and edge computing
International Journal of Intelligent Robotics and Applications (2021): 1-13. - 30.[Zhao 2020]
IoT edge computing-enabled collaborative tracking system for manufacturing resources in industrial park
Advanced Engineering Informatics 43 (2020): 101044. - 31.[Chen 2019]
iRAF: A Deep Reinforcement Learning Approach for Collaborative Mobile Edge Computing IoT Networks
IEEE Internet of Things Journal 6.4 (2019): 7011-7024. - 32.[Xu 2019 Computation]
A computation offloading method over big data for IoT-enabled cloud-edge computing
Future Generation Computer Systems 95 (2019): 522-533. - 33.[Singh 2020]
Hierarchical Security Paradigm for IoT Multiaccess Edge Computing
IEEE Internet of Things Journal 8.7 (2020): 5794-5805. - 34.[Nieves-Acaron 2021]
ACE: An ATAK Plugin for Enhanced Acoustic Situational Awareness at the Edge
MILCOM 2021-2021 IEEE Military Communications Conference (MILCOM). IEEE. - 35.[Wyatt 2021]
Environmental Sound Classification with Tiny Transformers in Noisy Edge Environments
2021 IEEE 7th World Forum on Internet of Things (WF-IoT). IEEE, 2021. - 36.[Elliott 2020]
Cyber-Physical Analytics: Environmental Sound Classification at the Edge
2020 IEEE 6th World Forum on Internet of Things (WF-IoT). IEEE, 2020. - 37.[Shen 2021]
The analysis of intelligent real‑time image recognition technology based on mobile edge computing and deep learning
Journal of Real-Time Image Processing 18.4 (2021): 1157-1166. - 38.[Gia 2019]
Edge AI in Smart Farming IoT: CNNs at the Edge and Fog Computing with LoRa
2019 IEEE AFRICON. IEEE, 2019. - 39.[Zhang 2021]
Trustworthy Target Tracking With Collaborative Deep Reinforcement Learning in EdgeAI-Aided IoT
IEEE Transactions on Industrial Informatics 18.2 (2021): 1301-1309. - 40. [Li, Tian 2020]
Federated Learning: Challenges, Methods, and Future Directions
IEEE Signal Processing Magazine 37.3 (2020): 50-60 - 41.[Cheng 2017]
A Survey of Model Compression and Acceleration for Deep Neural Networks
arXiv preprint arXiv:1710.09282 (2017). - 42.[Gim 2022]
Memory-efficient DNN training on mobile devices
ACM MobiSys’22 - 43.[Yang 2022]
Lead federated neuromorphic learning for wireless edge artificial intelligence
Nature Communications’22 - 44. [Sun 2022]
FedSEA: A Semi-Asynchronous Federated Learning Framework for Extremely Heterogeneous Devices
ACM SenSys’22 - 45. [Letaief 2021]
Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
IEEE Journal on Selected Areas in Communications