Composing Complex and Hybrid AI Solutions
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CABENCH: Benchmarking Composable AI for Solving Complex Tasks through Composing Ready-to-Use Models
Composable AI offers a scalable and effective paradigm for tackling complex AI tasks by decomposing them into sub-tasks and solving each sub-task using ready-to-use well-trained models. However, systematically evaluating…
Improved Modeling of Complex Systems Using Hybrid Physics/Machine Learning/Stochastic Models
Combining domain knowledge models with neural models has been challenging. End-to-end trained neural models often perform better (lower Mean Square Error) than domain knowledge models or domain/neural combinations, and …
BIG-bench Machine LearningTime SeriesTime Series AnalysisLearning to Reason with Curriculum II: Compositional Generalization
Compositional generalization, the ability to solve complex problems by combining solutions to simpler sub-problems, is a fundamental capability of both natural and artificial intelligence, and a key mechanism underlying …
Reinforcement LearningHybridGen: VLM-Guided Hybrid Planning for Scalable Data Generation of Imitation Learning
The acquisition of large-scale and diverse demonstration data are essential for improving robotic imitation learning generalization. However, generating such data for complex manipulations is challenging in real-world se…
Imitation LearningLanguage ModelingLanguage ModellingHybrid$^2$ Neural ODE Causal Modeling and an Application to Glycemic Response
Hybrid models composing mechanistic ODE-based dynamics with flexible and expressive neural network components have grown rapidly in popularity, especially in scientific domains where such ODE-based modeling offers import…
counterfactualCounterfactual ReasoningInductive Biasvalid