AI-Toolkit: a microservices architecture for low-code decentralized machine intelligence
Lomonaco V., Caro V. D., Gallicchio C., Carta A., Sardianos C., Varlamis I., Tserpes K., Coppola M., Marmpena M., Politi S., Schoitsch E., Bacciu D.
Decentralized Learning and Inference Pervasive Computing Microservice architectures Artificial Intelligence Computer architecture Production Signal processing Solids Rapid prototyping Outsourcing Microservices
Artificial Intelligence and Machine Learning toolkits such as Scikit-learn, PyTorch and Tensorflow provide today a solid starting point for the rapid prototyping of R&D solutions. However, they can be hardly ported to heterogeneous decentralised hardware and real-world production environments. A common practice involves outsourcing deployment solutions to scalable cloud infrastructures such as Amazon SageMaker or Microsoft Azure. In this paper, we proposed an open-source microservices-based architecture for decentralised machine intelligence which aims at bringing R&D and deployment functionalities closer following a low-code approach. Such an approach would guarantee flexible integration of cutting-edge functionalities while preserving complete control over the deployed solutions at negligible costs and maintenance efforts.
Publisher: IEEE
[2] Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., “Pytorch: An imperative style, high-performance deep learning library,” Advances in neural information processing systems, vol. 32, 2019.
[3] Mart´ın Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al., “Tensorflow: a system for large-scale machine learning.,” in Proc. of 12th USENIX OSDI. Savannah, GA, USA, 2016, pp. 265-283.
[4] Davide Bacciu, Siranush Akarmazyan, Eric Armengaud, Manlio Bacco, George Bravos, Calogero Calandra, Emanuele Carlini, Antonio Carta, Pietro Cassara`, Massimo Coppola, et al., “Teaching-trustworthy autonomous cyber-physical applications through humancentred intelligence,” in 2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS). IEEE, 2021, pp. 1-6.
[5] Valerio De Caro, Saira Bano, Achilles Machumilane, Alberto Gotta, Pietro Cassara`, Antonio Carta, Rudy Semola, Christos Sardianos, Christos Chronis, Iraklis Varlamis, et al., “Ai-as-a-service toolkit for humancentered intelligence in autonomous driving,” in 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops). IEEE, 2022, pp. 91- 93.
[6] David Dossot, RabbitMQ essentials, Packt Publishing Ltd, 2014.
[7] Benjamin A Clegg, Gregory J DiGirolamo, and Steven W Keele, “Sequence learning,” Trends in cognitive sciences, vol. 2, no. 8, pp. 275-281, 1998.
[8] Davide Maltoni and Vincenzo Lomonaco, “Semisupervised tuning from temporal coherence,” in 2016 23rd International Conference on Pattern Recognition (ICPR). IEEE, 2016, pp. 2509-2514.
[9] Jorge Rodr´ıguez-Arce, Liliana Lara-Flores, Otniel Portillo-Rodr´ıguez, and Rigoberto Mart´ınez-Me´ndez, “Towards an anxiety and stress recognition system for academic environments based on physiological features,” Computer methods and programs in biomedicine, vol. 190, pp. 105408, 2020.
[10] Christos Chronis, Christos Sardianos, Iraklis Varlamis, Dimitrios Michail, and Konstantinos Tserpes, “A driving profile recommender system for autonomous driving using sensor data and reinforcement learning,” in 25th Pan-Hellenic Conference on Informatics, 2021, pp. 33- 38.
[11] Pankaj Malhotra, Lovekesh Vig, Gautam M. Shroff, and Puneet Agarwal, “Long short term memory networks for anomaly detection in time series,” in The European Symposium on Artificial Neural Networks , 2015.
[12] Pankaj Malhotra, Anusha Ramakrishnan, Gaurangi Anand, Lovekesh Vig, Puneet Agarwal, and Gautam M. Shroff, “Lstm-based encoder-decoder for multi-sensor anomaly detection,” ArXiv, vol. abs/1607.00148, 2016.
[13] Georg Macher, Siranush Akarmazyan, Eric Armengaud, Davide Bacciu, Calogero Calandra, Herbert Danzinger, Patrizio Dazzi, Charalampos Davalas, Maria Carmela De Gennaro, Angela Dimitriou, et al., “Dependable integration concepts for human-centric ai-based systems,” in Computer Safety, Reliability, and Security. SAFECOMP 2021 Workshops: DECSoS, MAPSOD, DepDevOps, USDAI, and WAISE, York, UK, September 7, 2021, Proceedings 40. Springer, 2021, pp. 11-23.
[14] Davide Bacciu, Antonio Carta, Daniele Di Sarli, Claudio Gallicchio, Vincenzo Lomonaco, and Salvatore Petroni, “Towards Functional Safety Compliance of Recurrent Neural Networks,” in Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bologna, Italy, Dec. 2021.
[15] Vincenzo Lomonaco, “Continual learning with deep architectures,” 2019.
[16] Andrea Cossu, Davide Bacciu, Antonio Carta, Claudio Gallicchio, and Vincenzo Lomonaco, “Continual learning with echo state networks,” European Symposium on Artificial Neural Networks (ESANN) , 2021.
Metrics
Back to previous page
@inproceedings{oai:iris.cnr.it:20.500.14243/535421,
title = {AI-Toolkit: a microservices architecture for low-code decentralized machine intelligence},
author = {Lomonaco V. and Caro V. D. and Gallicchio C. and Carta A. and Sardianos C. and Varlamis I. and Tserpes K. and Coppola M. and Marmpena M. and Politi S. and Schoitsch E. and Bacciu D.},
publisher = {IEEE},
doi = {10.1109/icasspw59220.2023.10193222 and 10.5281/zenodo.8091679 and 10.5281/zenodo.8091680},
year = {2023}
}
0000-0002-7937-4157
TEACHING
A computing toolkit for building efficient autonomous applications leveraging humanistic intelligence
