Arm AIoT Dev Summit 2019
2019-12-02..2019-12-03
Mountain View, United States
| title | author | length |
|---|---|---|
| Building noise-immune speech interfaces for IoT | Chris Rowen | 34m |
Clear Command is an edge neural stack that trains a unified noise-robust model for vocabularies up to about 100 short phrases, fits code+model+RAM in… | ||
| Pelion Unified ID – the key to IoT at scale | Jerry Jun | 21m |
Pelion Unified ID unifies device identity from chip to cloud using SIM/eSIMs as a root of trust, PSA APIs and an IOT Security Applet to generate and store… | ||
| A full Arm IoT stack from sensors to the cloud | Carl Perry | 14m |
Complete Arm stack from sensors to cloud: Raspberry Pi endpoints run Arm Mbed and Python libraries, send temperature, humidity, barometric pressure, TVOC, eCO2… | ||
| Getting started with a self-driving RC car | Rahul Ravikumar, Ed Murphy | 35m |
Hands-on guide to building an RC self driver using Donkeycar hardware and Python software with a camera, a PCA9685 PWM board for steering and throttle, and… | ||
| Ethical AI | Timnit Gebru | 28m |
Analysis of commercial automatic gender recognition APIs shows error rates drop to near-random for darker-skinned women while lighter-skinned men have much… | ||
| Scaling the market with mobile IoT and security by design | Ian Smith | 31m |
GSMA projects 3.5 billion cellular IoT by 2025 and pushes LPWA rollouts using LTE-M and NB‑IoT; guidance focuses on endpoints and a mandatory trusted root. The… | ||
| Panel: Changing the Landscape of AIoT Together; The Importance of Diversity in Tech | Blair Palmer, Ciira Maina, Will Abbey | 30m |
Panel reports a concrete deployment of LoRa fire sensors in Nairobi covering dense settlements of ~7,000 people that connects to a control panel and dispatches… | ||
| Giving developers the keys to building the future | Simon Segars, Jem Davies, John Fry, Kidus Asfaw | 01h 08m |
Claimed hardware and software details: Cortex‑M Helium extensions yield Cortex‑M Helium: 15x ML uplift for tiny‑ML; TF‑Lite‑Micro and Arm’s CMSIS‑NN give 4–5x… | ||
| Racing Robocars | Chris Anderson | 23m |
A global DIY Robocar community of about 10,000 people across 40–50 regions builds wheel‑to‑wheel autonomous racers using cameras, Raspberry Pi or Jetson Nano… | ||
| Scalable ML acceleration with ONNX Runtime | Manash Goswami | 30m |
ONNX Runtime is an open‑source inference engine that converts TensorFlow/PyTorch models to ONNX and runs them via pluggable Execution Providers (OpenVINO… | ||
| Running AI/Neural networks on microcontrollers made simple with the STM32Cube.AI | Markus Mayr | 24m |
STM32Cube.AI converts pretrained Keras/Caffe/TensorFlow models into optimized C code that calls STM32 libraries and reports which MCU parts the model fits. It… | ||
| Maximize the performance of your ML platform with Arm software and tools | Raviraj Mahatme | 15m |
Technical session delivered by Raviraj Mahatme, Senior Product Manager for ML at Arm.
This session explores how to use Arm’s ML software libraries and tools… | ||
| Ci in IoT/Embedded: creating a simple, salable and automated workflow | Charles McCann | 12m |
Shows a concrete CI setup that runs a Linux Python app on Cortex‑A and a bare‑metal C app on Cortex‑M, with unit, integration and system tests automated and… | ||
| Next generation machine learning for mobile and embedded platforms | Rajen Bhatt | 26m |
Company claims a production ML platform that builds and compiles sensor models into C libraries, proven on ARM Cortex‑M0–M4 targets and used to ship 200… | ||
| AI workflow for large scale deployment of far-edge ML devices | Kabir Manghnani, Mark Stubbs | 17m |
System describes a concrete pipeline: peel-and-stick sensor with accelerometer and a cellular modem sends raw vibration to cloud, containerized training spins… | ||
| How we got rid of passwords in IoT | Carel Grove | 26m |
A password is replaced by certificate-based identity: a factory configurator utility runs in the factory, injects root CA certificates (bootstrap and LwM2M)… | ||
| Bootstrapping edge infrastructure for AIoT applications with open source software | Galem Kayo | 19m |
Claim: developers can bootstrap edge AIoT infrastructure on COTS hardware using open-source components and a few commands. The stack uses MicroStack in four… | ||
| Robot Operating System (ROS): current and future capabilities on embedded systems | Katherine Scott | 30m |
ROS is presented as a working stack from sensors to cloud: a DDS-backed ROS 2 pub/sub replaces ROS 1’s custom bus, tooling like rosbag record/replay captures… | ||
| Democratizing Innovation | Massimo Banzi | 30m |
A project that reduces friction claims to let anyone prototype connected products quickly: tiny boards with Wi‑Fi, Bluetooth and an ARM Cortex‑M0+/M4, 70… | ||
| What’s TinyML good for | Pete Warden | 27m |
Evidence that embedded ML runs at scale: TensorFlow Lite powers over 3 billion phones, and TensorFlow Lite Micro targets 1 mW budgets. Demonstrated artifacts… | ||
| Listen to your data: Swim builds AI models and predicts in real-time | Simon Crosby | 27m |
Swim automatically spins up stateful digital twins (tiny in-memory “web agents”) for each sensor, links neighbors, and runs streaming analytics and online… | ||
| Extending machine learning to industrial IoT applications at the edge with AWS | Ian Perez Ponce | 32m |
Claim: edge ML reduces latency and scales IIoT by moving inference on-device and retraining in cloud. Prototype: a Toradex module with an NXP i.MX8M and MIPI… | ||
| From concept to production: design and optimize computer vision applications on Arm | Dr. Nitin Gupta | 19m |
Roadmap from data to deployed vision app that actually runs on Arm hardware: use on-prem data collection and pixel-level annotation for domain-specific cases… | ||
| AIoT Dev Summit 2019 | 01m | |
We hope you had an amazing time at the #AIoTDevSummit in 2019! Here's a few highlights from the event. A huge thank you to everyone for joining us - we hope… | ||
| AIoT Dev Summit 2020 - China | 03m | |
Huge thank you to everyone that joined us at the #AIoTDevSummit in China! Here are a few highlights from the event. We hope you had an amazing time!
Stay… | ||
| nothing matches | ||