Archives: Presentations

PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++

Combinatorial-Randomness-Based Power Amplifier Datasets with RF Fingerprint Classification

Self-sustainable Wearable IoT Devices: Energy Harvesting, Management and Consumption

TinyMLOps: Overview, Challenges and Implementation

THIN-Bayes: Platform-Aware Machine Learning for Low-End IoT Devices

Tiny Transformers: Enabling Transformer Execution on Low-Power IoT Endnodes

CFU Playground: Full-Stack Open-Source Framework for TinyML Acceleration on FPGAs

QuantLab: a Modular Framework for Training and Deploying Mixed-Precision NNs

RedMulE – Reduced-Precision Matrix Multiplication Engine

Co-designing the hardware, ISA and software for RISC-V based tinyML processor