Train One Network and Specialize It for Efficient Deployment
Explore efficient neural network deployment across diverse devices using the Once-for-All network approach, which enables quick specialization without retraining and outperforms state-of-the-art methods on edge devices.
NRF9160 - Optimized for Ultra Low Power and Small Cellular IoT Applications
Explore nRF9160 SiP for ultra-low power cellular IoT: LTE-M/NB-IoT connectivity, small form factor, extended battery life, GPS capabilities, and edge computing potential for innovative IoT applications.
Secure & Democratize the Data in Your Customer's Brownfield Devices
Secure legacy devices, add cybersecurity, and integrate operational data into modern IIoT infrastructure using edge programmable industrial controllers for digital transformation initiatives.
Visual AI in Milliwatts - A Grand Challenge and Massive Opportunity
Explore visual AI's potential in low-power devices, discussing challenges, opportunities, and applications in security cameras and beyond. Learn about deep learning, processors, and algorithms driving this technology.
tinyMLPerf: Benchmarking Ultra-low Power Machine Learning Systems
Explore benchmarking for ultra-low power ML systems, focusing on tinyMLPerf's methodology, tasks, and ecosystem impact. Learn about quantization and community-driven efforts in this emerging field.
Energy-efficient On-device Processing for Next-generation Endpoint ML - tinyML Summit 2020
Explore energy-efficient on-device processing for endpoint machine learning, focusing on Arm's Cortex-M55 CPU and Ethos-U55 NPU for next-generation AI applications.
Resource Efficient Machine Learning in a Few KBs of RAM - tinyML Summit 2020
Explore resource-efficient machine learning techniques for IoT devices with limited RAM, focusing on Microsoft's EdgeML library and algorithms like ProtoNN and FastRNN for edge computing.
TinyML Talks - Review of the TinyML EMEA Forum - The Seeds Have Been Planted, Time for the EMEA
Comprehensive review of the inaugural tinyML EMEA Forum, highlighting key events, discussions, and future directions for the tinyML movement in Europe, Middle East, and Africa.
Avoiding Loss of Quality in Tiny Models - Neuton.ai Partner Session
Explore compact AI models without sacrificing quality. Learn to assess model quality, understand decision-making logic, evaluate training data, and interpret model outputs for tinyML applications.
The Model Efficiency Pipeline: Enabling Deep Learning Inference at the Edge
Explore optimizing deep learning for edge devices through model efficiency techniques, including neural architecture search, pruning, quantization, and conditional processing.
tinyML Vision Challenge - Intel-Luxonis DepthAI Platform Overview
Explore Intel and Luxonis' DepthAI platform for advanced vision solutions. Learn about AI inference, OpenVINO toolkit, and developing spatial edge applications using the LUX-ESP32 device.
tinyML: Impact and Growth of Always-On Devices
Explore the growing impact of tinyML devices in everyday life, from always-on voice in phones to environmental sensing in machines, and learn about the market's rapid expansion and technological requirements.
Hardware Aware Training for Efficient Keyword Spotting - tinyML Research Symposium 2021
Explore hardware-aware training for efficient keyword spotting, focusing on Legendre Memory Unit networks to achieve state-of-the-art accuracy and power efficiency on various hardware platforms.
Advanced Network Quantization and Compression Using AIMET - tinyML Summit 2021
Explore advanced network quantization and compression techniques using AIMET to optimize AI models for efficient deployment on end devices, addressing memory, compute, and energy constraints.
Powering the Next Generation of IoT with Embedded Machine Learning
Unlock IoT potential with Edge Impulse machine learning and Nordic's low-power wireless solutions. Learn to create motion detection, sound recognition, and image classification on edge devices using nRF52840 and nRF5340 kits.
NRF9160 - Putting the "Smarts" Into Smart Meters
Explore how nRF9160 SiP enables smart meters with cellular IoT, solving connectivity, flexibility, and power challenges for efficient utility metering and cloud integration.
Accelerate Edge Compute with Syntiant's TinyML Platform
Explore Syntiant's TinyML platform for efficient edge AI in battery-powered devices, featuring Neural Decision Processors for enhanced processing and power efficiency compared to MCUs.
De-risking Embedded Machine Learning Projects Using Novel Technologies
Explore novel technologies for successful embedded machine learning projects, addressing challenges and ensuring customer success through innovative design and engineering philosophies.
Efficient On-Device Deep Learning: Challenges and Opportunities
Explore efficient on-device deep learning, focusing on affordable AI models for edge devices and maximizing inference performance using heterogeneous computing resources.
Endpoint AI Revolution Driven by Standardized Computing Platform
Explore the Endpoint AI revolution with Arm's standardized computing platform, focusing on TinyML applications, robust software stacks, and specialized processors for efficient machine learning on IoT devices.
Machine Learning at the Extreme Edge of Always-on Intelligent Sensor Networks
Explore ML optimization techniques for resource-constrained IoT sensor nodes, focusing on system, algorithm, architecture, and circuit levels to achieve significant area-power improvements.