Introduction to optimization algorithms for compressing neural networks

The extreme compression of LSTM models using sparse structured additive matrices

GAP8: A Parallel, Ultra-low-power and flexible RISC-V based IoT Application Processor for the TinyML ecosystem

Cutting the AI Power Cord: Technology to Enable True Edge Inference

AI/ML solutions for low-power Edge platforms – challenges and opportunities

Democratization of Artificial Intelligence (AI) to Small Scale Farmers – a framework to deploy AI Models to Tiny IoT Edges that operate in constrained environments

Qeexo’s Runtime-Free Architecture for Efficient Deployment of Neural Networks on Embedded Targets

Embedded ML research at TUM: Moving NN Inference to the Extreme Edge

Building Products using Edge AI / TinyML on MCUs

Running TF Lite on Microcontrollers without hardware in Renode