Archives: Presentations

Novel method for Ultra-Low-Footprint Keyword-Spotting

Highlights of architecture optimizations for ultra-low power inference on larger CNNs

Bio-Inspired Edge Learning on the Akida Event-Based Neural Processor

SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers

End-to-End Sound Classification On Loihi Neuromorphic Chip

High-Efficiency Neural Network Inference using DesignWare ARC EMxD Processors & TensorFlow Lite for Microcontrollers

TSM: Temporal Shift Module for Efficient Video Understanding

Engineering tinyML models in sound recognition. An analysis of an entire specialist pipeline, from data collection to deployment

tinyML Perf: Expanding the MLPerf Inference benchmark to microcontrollers and tiny devices

Using ML for ML to Span the Gamut of TinyML Hardware