Edge analysis compact AI “ennbed”
Cotofure Co., Ltd.

About This Product

Built-in deep learning system "ennbed" that learns on a PC and executes on a microcontroller.Using microcontroller deep learning, the wireless communication technology LPWA (Low Power Wide Area) for IoT and AI operation on devices cheaper than smartphones are realized. You can make it happen.

In recent years, demand has increased as all kinds of devices have become smarter, and they are expected to be used in a wide range of fields. Catalina's edge analysis compact AI was developed with the keywords of "low cost," "high-speed response," and "low power consumption" in hopes of helping customers solve problems that were previously impossible to achieve. .

Features
■Smart equipmentDeep learning is possible to meet the increasing sophistication of user requirements

■StandaloneOperates without network Applicable to various devices

■Low costNo cloud operation costs required

■Fast responseBecause there is almost no network delay, high-speed response is possible when processing on embedded equipment.

■Security, privacyPrevent data leaks by processing data at your fingertips

Feature comparison
■ConventionalTo use a PC framework on an embedded device, it requires tens of MB of ROM/RAM and a smartphone-class CPU.

■ennbedLearning is done with Caffe on the PC, so there is no need to learn new tools.
"ennbed" performs compression processing while maintaining the accuracy of learning results, achieving a minimum of several dozen KB of ROM/RAM consumption.