The next generation of artificial intelligence: Synthesizable AI
Document Type
Conference Proceeding
Publication Date
1-1-2019
Abstract
While AI is expanding to many systems and services from search engines to online retail, a revolution is needed, to produce rapid, reliable “AI everywhere” applications by “continuous, cross-domain learning”. We introduce Synthesizable Artificial Intelligence, and discuss its uniqueness by its five advanced “abilities”; (1) continuous learning after training by “connecting the dots”; (2) measuring quality of success; (3) correcting concept drift; (4) “self-correcting” for new paradigms; and (5) retroactively applying new learning for development of “long-term self-learning”. SAI can retroactively apply new concepts to old examples, “self-learning” in a new way by considering recent experiences similar to the human experience. We demonstrate its current and future applications in transferring seamlessly from one domain to another, and show its use in commercial applications, including engine sound analysis, providing real-time indications of potential engine failure.
Publication Source (Journal or Book title)
Advances in Intelligent Systems and Computing
First Page
659
Last Page
677
Recommended Citation
Mukhopadhyay, S., Iyengar, S., Madni, A., & Di Biano, R. (2019). The next generation of artificial intelligence: Synthesizable AI. Advances in Intelligent Systems and Computing, 880, 659-677. https://doi.org/10.1007/978-3-030-02686-8_50