Resources of our survey paper "Optimizing Edge AI: A Comprehensive Survey on Data, Model, and System Strategies"

[ICLR2022] Efficient Split-Mix federated learning for in-situ model customization during both training and testing time

Benchmarking machine learning inferencing on embedded hardware.

Epsilon is a library with functions for machine learning and statistics written in plain C. It is intended to run on microcontrollers.

This project focuses on the implementation of optimized Linear and DNN regression models for inter-vehicle distance prediction in a Cooperative Adaptive Cruise Control (CACC) application. It leverages Tensorflow Lite to create optimized models through quantization and pruning for realtime inferencing on Raspberry Pi and On-board Unit (OBU) of Co…

An On-Device completely offline personal AI Agent that has both user interface and an always-active kernel-level interface that can interact with the programs you write and the apps you run.

Ingenuity is an optimized inference engine and benchmarking tool for TinyML models on embedded IoT devices.

A Smart Mask Enforcement System using Multitenant Cascading Architecture in TinyML

Practical work developed for the subject internet of things/embedded systems. My Replenisher is a complete end-to-end application, ranging from TinyMl with arduino nano 33 ble, communication with ESP32 to a mobile application that embodies the entire final scope.

Tiny implementation of kernel passive-aggressive regression on a budget in C.

Embedded Software: Running machine learning models on Raspberry Pi

The official Edge Impulse firmware for PSoC63 (CY8CKIT-062-BLE)

A fully embedded light temperature control system capable of matching real-world sunlight color using artificial tunable white LEDs. Utilizes onboard tiny ML with Tensorflow lite regression models. Designed for use as photographic softbox lights, it provides precise lighting that match the natural sunlight.