Composing Complex and Hybrid AI Solutions
This work provides a framework for composing complex and hybrid AI solutions, addressing the need for efficient experimentation and interchangeable components in AI development, though it is incremental as it builds on an existing system.
The authors extended the Acumos system to support general AI applications by adding features like gRPC/Protobuf interfaces, automatic orchestration of graphical assemblies, and provisions for user interfaces and shared storage, enabling deployable solutions as demonstrated on a public framework.
Progress in several areas of computer science has been enabled by comfortable and efficient means of experimentation, clear interfaces, and interchangable components, for example using OpenCV for computer vision or ROS for robotics. We describe an extension of the Acumos system towards enabling the above features for general AI applications. Originally, Acumos was created for telecommunication purposes, mainly for creating linear pipelines of machine learning components. Our extensions include support for more generic components with gRPC/Protobuf interfaces, automatic orchestration of graphically assembled solutions including control loops, sub-component topologies, and event-based communication,and provisions for assembling solutions which contain user interfaces and shared storage areas. We provide examples of deployable solutions and their interfaces. The framework is deployed at http://aiexp.ai4europe.eu/ and its source code is managed as an open source Eclipse project.