IEEE 3301-2022

The MPAI AI Framework (MPAI-AIF) Technical Specification specifies architecture, interfaces, protocols and Application Programming Interfaces (API) of an AI Framework (AIF), especially designed for execution of AI-based implementations, but also suitable for mixed AI and traditional data processing workflows. MPAI-AIF possesses the following main features: • Operating System-independent. • Component-based modular architecture with standard interfaces. • Interfaces encapsulate Components to abstract them from the development environment. • Interface with the MPAI Store enables access to validated Components. • Component can be implemented as: software only (from Micro-Controller Units to High-Performance Computing), hardware only, and hybrid hardware-software. • Component system features are: • Execution in local and distributed Zero-Trust architectures. • Possibility to interact with other Implementations operating in proximity. • Direct support to Machine Learning functionalities.



New IEEE Standard - Active. This standard adopts MPAI AI Framework (MPAI-AIF) Technical Specification Version 1.1 as an IEEE Standard. The MPAI-AIF Technical Specification specifies architecture, interfaces, protocols, and Application Programming Interfaces (API) of an AI Framework (AIF), especially designed for the execution of AI-based implementation, but also suitable for mixed AI and traditional data processing workflow.