Composing Complex and Hybrid AI Solutions
- URL: http://arxiv.org/abs/2202.12566v1
- Date: Fri, 25 Feb 2022 08:57:06 GMT
- Title: Composing Complex and Hybrid AI Solutions
- Authors: Peter Sch\"uller, Jo\~ao Paolo Costeira, James Crowley, Jasmin
Grosinger, F\'elix Ingrand, Uwe K\"ockemann, Alessandro Saffiotti, Martin
Welss
- Abstract summary: We describe an extension of the Acumos system towards enabling the above features for general AI applications.
Our extensions include support for more generic components with gRPC/Protobuf interfaces.
We provide examples of deployable solutions and their interfaces.
- Score: 52.00820391621739
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning [74.58666091522198]
We present a framework for intuitive robot programming by non-experts.
We leverage natural language prompts and contextual information from the Robot Operating System (ROS)
Our system integrates large language models (LLMs), enabling non-experts to articulate task requirements to the system through a chat interface.
arXiv Detail & Related papers (2024-06-28T08:28:38Z) - A Hybrid Execution Environment for Computer-Interpretable Guidelines in PROforma [42.15267357325546]
We develop a hybrid execution environment for computer-interpretable guidelines (CIGs) in PROforma.
The proposed environment is part of the CAPABLE system which provides coaching for cancer patients and decision support for physicians.
arXiv Detail & Related papers (2024-04-07T16:32:37Z) - LExCI: A Framework for Reinforcement Learning with Embedded Systems [1.8218298349840023]
We present a framework named LExCI, which bridges the gap between RL libraries and embedded systems.
It provides a free and open-source tool for training agents on embedded systems using the open-source library RLlib.
Its operability is demonstrated with two state-of-the-art RL-algorithms and a rapid control prototyping system.
arXiv Detail & Related papers (2023-12-05T13:06:25Z) - Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene
Segmentation [58.74791043631219]
We propose a novel framework STswinCL that explores the complementary intra- and inter-video relations to boost segmentation performance.
We extensively validate our approach on two public surgical video benchmarks, including EndoVis18 Challenge and CaDIS dataset.
Experimental results demonstrate the promising performance of our method, which consistently exceeds previous state-of-the-art approaches.
arXiv Detail & Related papers (2022-03-29T05:52:23Z) - Enabling Cross-Domain Communication: How to Bridge the Gap between AI
and HW Engineers [0.17205106391379021]
A key issue in system design is the lack of communication between hardware, software and domain expert.
Recent research work shows progress in automatic HW/SW co-design flows of neural accelerators.
This position paper discusses possibilities how to establish such a methodology for systems that include (reconfigurable) dedicated accelerators.
arXiv Detail & Related papers (2021-04-08T14:05:15Z) - Composable Learning with Sparse Kernel Representations [110.19179439773578]
We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space.
We improve the sample complexity of this approach by imposing a structure of the state-action function through a normalized advantage function.
We demonstrate the performance of this algorithm on learning obstacle-avoidance policies in multiple simulations of a robot equipped with a laser scanner while navigating in a 2D environment.
arXiv Detail & Related papers (2021-03-26T13:58:23Z) - A Data-Centric Framework for Composable NLP Workflows [109.51144493023533]
Empirical natural language processing systems in application domains (e.g., healthcare, finance, education) involve interoperation among multiple components.
We establish a unified open-source framework to support fast development of such sophisticated NLP in a composable manner.
arXiv Detail & Related papers (2021-03-02T16:19:44Z) - Towards an Interface Description Template for AI-enabled Systems [77.34726150561087]
Reuse is a common system architecture approach that seeks to instantiate a system architecture with existing components.
There is currently no framework that guides the selection of necessary information to assess their portability to operate in a system different than the one for which the component was originally purposed.
We present ongoing work on establishing an interface description template that captures the main information of an AI-enabled component.
arXiv Detail & Related papers (2020-07-13T20:30:26Z) - Project CLAI: Instrumenting the Command Line as a New Environment for AI
Agents [12.310004080500082]
CLAI aims to bring the power of AI to the command line interface (CLI)
We discuss the design and implementation of the platform in detail, through illustrative use cases of new end user interaction patterns.
We report on some early user feedback on CLAI's features from an internal survey.
arXiv Detail & Related papers (2020-01-31T05:01:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.