| Date |
Discussion Topics and Papers |
| W1 – 1.24 |
Course introduction and logistics |
| W2 – 1.31 |
Fundamentals of Embedded Systems and AI/ML |
| W3 – 2.7 |
TinyML (Vijay Janapa Reddi, Harvard)
paper 1: A Survey of Model Compression and Acceleration for Deep Neural Networks [Yunfan Cai]
paper 2: MobileNetV2: Inverted Residuals and Linear Bottlenecks [Sara Sun]
paper 3: A First Look at Deep Learning Apps on Smartphones [Wenpu Wang]
paper 4: IoT edge computing-enabled collaborative tracking system for manufacturing resources in industrial park [Runfeng Huang] |
| W4 – 2.14 |
Hardware AI/ML Accelerators (Zhangxi Tan, RIOS Lab)
paper 1: Experiments and optimizations for TVM on RISC-V Architectures with P Extension [Xunqi Li]
paper 2: Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application [Sophie Liu]
paper 3: TinyML Platforms Benchmarking [Yuqi Zhu]
paper 4: An evaluation of edge tpu accelerators for convolutional neural networks [Botong Xiao] |
| W5 – 2.21 |
Embedded Data (Jorge Ortiz, Rutgers)
paper 1: Quantized neural networks: Training neural networks with low precision weights and activations [Baizhou (David) Hou]
paper 2: Survey and benchmarking of machine learning accelerators [Chuan-Tung Lin]
paper 3: License plate segmentation and recognition system using deep learning and OpenVINO [Perry Flamer]
paper 4: Shufflenet v2: Practical guidelines for efficient cnn architecture design [Kevin Jiang] |
| W6 – 2.28 |
Federated Learning and Mobile AI (Nic Lane, Cambridge)
paper 1: TVM: end-to-end optimization stack for deep learning [Kaiyuan Hou]
paper 2: Environmental Sound Classification with Tiny Transformers in Noisy Edge Environments [Srivatsan]
paper 3: Towards federated learning at scale: System design [Lanxiang Hu]
paper 4: FEEL: A Federated Edge Learning System for Efficient and Privacy-Preserving Mobile Healthcare [Yousuf Baker] |
| W7 – 3.7 |
Scalable AI (Matt Welsh, OctoML)
paper 1: MediaPipe: A Framework for Building Perception Pipelines [Yuxin Wang]
paper 2: A survey on methods and theories of quantized neural networks [Yifan Zhan]
paper 3: Shufflenet: An extremely efficient convolutional neural network for mobile devices [Manisha Rajkumar]
paper 4: Efficient Execution of Quantized Deep Learning Models: A Compiler Approach [Qingxin Cheng] |
| W8 – 3.14 |
Spring break (no class) |
| W9 – 3.21 |
Tutorial: TensorFlow Lite Micro
paper 1: Micronets: Neural network architectures for deploying tinyml applications on commodity microcontrollers [Dewei Wang]
paper 2: Tensorflow lite micro: Embedded machine learning on tinyml systems [Hanshan Li]
paper 3: Mobilenets: Efficient convolutional neural networks for mobile vision applications [Yinsen Jia]
paper 4: Intel ngraph: An intermediate representation, compiler, and executor for deep learning [Junyu Li] |
| W10 – 3.28 |
Tutorial: TVM/uTVM (Gavin Uberti, OctoML)
paper 1: Benchmarking TPU, GPU, and CPU Platforms for Deep Learning [Angel Estigarribia]
paper 2: Mnn: A universal and efficient inference engine [Isha Garg]
paper 3: Trustworthy Target Tracking With Collaborative Deep Reinforcement Learning in EdgeAI-Aided IoT [Aashi Kapoor]
paper 4: Tuning of the Structure and Parameters of a Neural Network Using an Improved Genetic Algorithm [Shangru Li] |
| W11 – 4.4 |
Tutorial: TensorFlow Lite Micro
paper 1: Federated Learning: Challenges, Methods, and Future Directions [Mandy Zhong]
paper 2: Mediapipe hands: On-device real-time hand tracking [Yunfan Gao]
paper 3: Edge Computing with Embedded AI: Thermal Image Analysis for Occupancy Estimation in Intelligent Buildings [Angzi Xu]
paper 4: Intelligent warehouse monitoring based on distributed system and edge computing [Chaoyu Fan] |
| W12 – 4.11 |
Acoustic AI (Stephen Xia) 10:10am to 11:00am
Entrepreneurship (Thomas Cheng, Brava) 11:00am to 11:30am
paper 1: The analysis of intelligent real‑time image recognition technology based on mobile edge computing and deep learning [Richard Samoilenko]
paper 2: Edge AI in Smart Farming IoT: CNNs at the Edge and Fog Computing with LoRa [Abhijeet Nayak]
paper 3: A computation offloading method over big data for IoT-enabled cloud-edge computing [Johanan Sowah]
paper 4: Computer Science as Empirical Enquiry: Symbol and Search [Muneer Khan]
paper 5: STEC-IoT: A Security Tactic by Virtualizing Edge Computing on IoT [Shuai Zhang] |
| W13 – 4.18 |
Embedded AI in Structures (Shijia Pan, UC Merced)
paper 1: Cyber-Physical Analytics: Environmental Sound Classification at the Edge [Longyi Li]
paper 2: SCEH: Smart Customized E-Health Framework for Countryside Using Edge AI and Body Sensor Networks [Jeongwook Lee]
paper 3: An Internet-of-Medical-Things-Enabled Edge Computing Framework for Tackling COVID-19 [Spandan Das]
paper 4: iRAF: A Deep Reinforcement Learning Approach for Collaborative Mobile Edge Computing IoT Networks [Krishan Kumar] |
| W14 – 4.25 |
Federated Learning in Health AI (Robert Dickerson, Babylon Health)
paper 1: Towards Artificial Intelligence Driven Emotion Aware Fall Monitoring Framework Suitable for Elderly People with Neurological Disorder [Shibo Sheng]
paper 2: Hierarchical Security Paradigm for IoT Multiaccess Edge Computing [Sakshi Gulgulia]
paper 3: ACE: An ATAK Plugin for Enhanced Acoustic Situational Awareness at the Edge [Rui Chu]
paper 4: In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning [Junyi Wu] |
| W15 – 5.2 |
Project Gala |