Stars
This is the Arduino® compatible port of the AIfES machine learning framework, developed and maintained by Fraunhofer Institute for Microelectronic Circuits and Systems.
This project implements a Convolutional Neural Network (CNN) in C using the AIfES framework. The model (in `main.c`) classifies MNIST images and displays the resulting accuracy. A Python script (`m…
[SenSys'24] PieBridge: Fast and Parameter-Efficient On-Device Training via Proxy Networks
A template-based, layer-oriented High Level Synthesis Tool for AI algorithms
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Course materials for MIT6.5940: TinyML and Efficient Deep Learning Computing
A C++ deep learning library for the construction and optimization of neural networks ranging from simple feedforward architectures to state-of-the-art convolutional ResNets and LSTMs.
Feedforward neural network with Backpropagation learning based on Eigen library
This repo is for Efinix TinyML platform, which offers end-to-end flow that facilitates TinyML solution deployment on Efinix FPGAs.
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
An implementation of DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers
A "large" language model running on a microcontroller
A higher-level Neural Network library for microcontrollers.
A lightweight neural network library for ESP32 and Arduino, enabling on-device training and simple predictions like XOR. Ideal for microcontroller-based AI projects with resource constraints. 🔧🚀
Haoyu-R / pocketnn
Forked from jaewoosong/pocketnnThe official, proof-of-concept C++ implementation of PocketNN.
This repo contains the code developed for my master thesis
Floating-Point Optimized On-Device Learning Library for the PULP Platform.
Introduction to Machine Learning Systems
Miro[ACM MobiCom '23] Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
Declarative way to run AI models in React Native on device, powered by ExecuTorch.