This presentation shortly presents an overview of researching activation types of Artificial Neural Networks, namely combinations of different activation cycles and activation rates, in context of interwoven cognitive production networks. It presents a simulation system, experiments using this simulation system as well as management interventions to reduce inefficiencies. This has been based on 14 novel forms of rhythmic state descriptions for dynamic systems.
00:00 Introduction
00:34 Motivation for Researching Interwoven Cognitive Production Networks
03:29 Design of Interlinked ANN-Based Production Systems
17:10 Experiments on Multi-Site ANN-Based Production Chains
24:05 Management Interventions for Avoiding Inefficiencies
25:26 Conclusion
26:57 References
You can find futher information at the corresponding article:
Grum, M. (2024a). Managing Multi-Site Artificial Neural Networks' Activation Rates and Activation Cycles - Demonstrating the Effects of Activation Types on ANN-based Cyber-Physical Production Systems. In: Technical Report BIS-AI-AS-2024-01, First Edition, January 2024, J.-Chair of Business Information Systems, esp. AI-based Appl. Sys., University of Potsdam, Potsdam, Germany.github.com/MarcusGrum/AI-CPS/blob/main/documentation/experiment05/publications/TechnicalReport_BIS-AI-AS-2024-01.pdf
Grum, M. (2024b). Researching Multi-Site Artificial Neural Networks’ Activation Rates and Activation Cycles. In: Shishkov, B. (eds) Business Modeling and Software Design. BMSD 2024. Lecture Notes in Business Information Processing, vol 523. Springer, Cham.
Grum, M. (2024c). Managing Multi-site Artificial Neural Networks’ Activation Rates and Activation Cycles. In: Shishkov, B. (eds) Business Modeling and Software Design. BMSD 2024. Lecture Notes in Business Information Processing, vol 523. Springer, Cham.
You can find further details at my public github repository:
Grum, M. (2024d). AI-CPS-Repository, github.com/MarcusGrum/AI-CPS/tree/main