Proving the Business Case for the Internet of Things

Access and LeapMind put AI on edge devices

Steve Rogerson
October 16, 2018
 
Japanese companies Access and LeapMind are collaborating to integrate edge computing and AI technology to achieve high-speed, real-time AI processing on edge devices.
 
Around 30 billion IoT devices are expected to be connected by 2020, ranging from high-end devices such as connected cars to low-end devices with limited power consumption and footprints such as surveillance monitors, small cameras and drones. The market expects AI technology to be combined with the ever-increasing number and types of IoT devices to drive take-up and effectiveness.
 
Demand is expected to be particularly high for the provision of tools to implement AI technology to achieve real-time image recognition on IoT edge devices and manage them in an efficient, secure and safe manner.
 
In light of this, the two companies are combining Access' technology for managing edge devices in the cloud remotely with LeapMind's model compression technology, which equips small computing environments, including low power consumption SoC FPGAs, with deep-learning inference algorithms.
 
Specifically, the combination of Access' NetFront edge AI with LeapMind's Delta-Lite will be used to build deep-learning models, distributing them to each edge device and updating them, thereby helping companies efficiently deploy and operate IoT services.
 
Targeting low-cost, low-power consumption edge devices, this makes it possible to implement recognition features on various edge devices such as small cameras that were not previously able to use deep learning.
 
"I am sure that this collaboration with Access will accelerate the implementation of deep learning of things, in which deep learning technology is applied to all kinds of objects,” said Soichi Matsuda, CEO of LeapMind. “Going forward, LeapMind will strive to make complex and complicated deep learning compact and simple and embed it to the real world."
 
Access and LeapMind will provide this integration to several companies in advance as a pilot test and will offer it officially by the end of the year to factories, warehouses, logistics, security and other fields that are working to equip their numerous IoT devices with AI.
 
"This collaboration with LeapMind makes it possible to actively implement AI technology on embedded devices,” said Michi Uematsu, CTO of Access. “Access has been continuously transforming society by providing internet technology to various embedded devices. By providing IoT devices powered by LeapMind's AI technology for embedded devices and Access' edge-computing technology for embedded devices, we will keep improving everyone's daily life."