AI CORE
1) AI embedded Hardware
< AION™ AI resources included in the series of Hardware>
PyTorch
PyTorch is an open source machine learning framework that accelerates the path from research prototyping to production deployment. AION™ caters PyTorch as an organizer, a controller, a compiler and a manager of AI relevant resources in the computing resources at the edge(on-premise).
TensorFlow
(version is flexible)
TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications. AION™ provides default components as basic tools, libraries and software resources at initial delivery for users.
Keras
(version is flexible)
Keras is an open-source neural-network library written in Python. It is capable of running on top of TensorFlow. AION™ prepared Keras as an initialized package on the AI stack embedded in the hardware.
Node.js
(version is flexible)
Node.js is an open-source focusing on backend engineering and running, dedicated to any type of data transferring and data processing. AION™ deploys fundamental and holistic Node.js environment as a framework and sets of source codes / libraries as the core of backend resources.
Nestjs
(version is flexible)
A progressive Node.js framework for building efficient, reliable and scalable applications. AION™ well harnesses Nestjs framework in order to adopt microservice oriented architecture and agile methods based on Node.js technologies.
ReactJS(version is flexible)
ReactNative(version is flexible)
DGLux5(Optional)
React is a JavaScript library for building user interfaces. It is maintained by Facebook and a community of individual developers and companies. React can be used as a base in the development of single-page or mobile applications, as it is optimal for fetching rapidly changing data that needs to be recorded. AION™ provides full sets of microservice oriented frontend architecture as an initial delivery hardware model. DGLux5 is optional, to enhance the quality and flexibility of UI and dashboard which is onboarding on the edge devices.
AI Models(Image, Voice)
AION™ distributes segregated AI Models as microservices with some datasets and learned SDKs including tech segments of Image Recognition and Voice Recognition. AION™ harnesses the opensource of YOLO as part of Image Visioning resources and some selected useful voice recognition open sources for comprehensive recognition of surrounding voices.
MongoDB
(version is flexible)
MongoDB is a cross-platform document-oriented database program. Classified as a NoSQL database program, MongoDB uses JSON-like documents with schema. AION™ provides data stacks of MongoDB as data engineering, preparing, provisioning cores of AI environment on the edge.
Docker
(version is flexible)
Docker is a set of coupled software-as-a-service and platform-as-a-service products that use operating-system-level virtualization to develop and deliver software in packages called containers. AION™ adopted Docker as a container center technology of the AION Platform.
Kubernetes
(version is flexible)
Kubernetes is an open-source container-orchestration system for automating application deployment, scaling, and management. AION™ embarked the dominant container orchestration technology as an edge computing resource orchestration stack with a remarkable patent application to Japanese Patent Office.
