Maieutic, Natural, and Artificial Forms in Automatic Control Case Study
Abstract
1. Introduction
Structure of the Paper
- Section 2 examines the current challenges in Automatic Control.
- Section 3 presents a concise overview of the conceptual and historical significance of the maieutic method with a mathematical model example.
- Section 4 offers a transcription of a real dialogue that exemplifies the application of the method, with a mathematical model and a cognitive map of the learning process.
- Section 5 reflects on the experiment of engaging ChatGPT in this intellectual journey.
- Section 6 summarizes the main contributions of the paper.
- An appendix follows, showcasing a ChatGPT research proposal.
2. Conceiving the General Challenge Problem of Automatic Control
- The three sets: U, X, y
- A set of input functions .
- The output transformation function, defined as
- The state transition function, defined asThis transformation associates each initial state, initial time, and input function to the state X of the system.
3. Maieutics as a Tool
3.1. A Brief Review
- Science Education and Pedagogy: In science teaching, especially at higher levels, Socratic questioning helps students develop critical thinking and deepen conceptual understanding.Example: Teaching physics or biology through guided inquiry questions rather than formal lectures.
- Philosophy of Science and Scientific Inquiry: Philosophers of science use maieutic dialogue (as in PHI by Tononi) to explore foundational questions about consciousness, cognition, and scientific explanation. Dialogues help reveal assumptions and foster theoretical development.
- Interdisciplinary Research and Collaboration: When teams from different scientific fields collaborate, dialogical inquiry—akin to maieutics—helps integrate perspectives and clarify concepts. Questioning fosters mutual understanding and uncovers hidden premises.
- Qualitative Research Methods: In the social sciences (e.g., psychology, anthropology, sociology), maieutic-like interviewing (open-ended, reflective questioning) enables participants to articulate deeper insights about their experiences.Examples: Narrative interviews, phenomenological research.
- Cognitive Science and AI: In AI research and cognitive science, dialogue systems or interactive learning environments can be inspired by maieutic principles, encouraging both machines and users to uncover knowledge through structured questioning.
- Plato, Meno: Classic example where Socrates helps a slave boy “remember” geometry through guided questioning [9].
- Plato, Theaetetus: Dialogue exploring the nature of knowledge through the questioning of assumptions [8]
- John L. Casti, The Cambridge Quintet: Fictional dialogue among great minds discussing AI and consciousness via Socratic exchange [1].
- Giulio Tononi, PHI: A Voyage from the Brain to the Soul: A fictional Galileo learns about consciousness through dialogical inquiry [2].
- Paulo Freire, Pedagogy of the Oppressed: Advocates dialogical education in which learners discover knowledge through critical questioning [10].
- Nancy Kline, Time to Think: Demonstrates how thoughtful questioning enables deep reflection and insight [11].
- Michael Bungay Stanier, The Coaching Habit: Applies maieutic techniques to coaching, using open questions to unlock client thinking [12].
- Carl Rogers, On Becoming a Person: Client-centered therapy where individuals discover their own truths through dialogic engagement [13].
- Danilo Dolci, Inventare il Futuro: Describes reciprocal maieutic dialogue for community education and empowerment [14].
- Boethius, The Consolation of Philosophy: A philosophical dialogue employing maieutic questioning to attain understanding [15].
- Vincenzo Manca, Conversazioni Artificiali—Conversazioni ai tempi dei Chatbot: A timely reflection linking maieutics to modern tools like ChatGPT, potentially becoming a landmark book on the topic [16].
3.2. Maieutics Is a Dynamical Process
- The Socratic Questioner (maieutic question);
- The interlocutor;
- The dialogic state space, including the set of possible cognitive states;
- Question, answer, operation.
- This is a stimulus or attentional cue that triggers neural processes towards a specific task.
- The interlocutor can be viewed as the network of neurons representing the current epistemic cognitive state. Each component corresponds to the activation level of a concept or memory mode.
- It represents the cognitive landscape of possible neural activation patterns like a high-dimensional attractor space in a recurrent neural network.
- That a mechanism possibly includes the external input neural computational layout made by sensory and cognitive prompts, with response of neuron population and generation of synapses or network level updates.
- Step 1: A randomly generated epistemic state is generated, being .
- Step 2: The socratic questioning is established. At each turn, the system selects the “weakest” dimension. That, in the selected example, is the smallest absolute value in , that in our case, corresponds to the second element. The question vector Q that is, in the context of dynamical systems, the forcing vector u, is a vector of the same dimension of made by zeros and a unity value that will result in .
- Step 3: The receptivity to the question does work on how well aligned it is with the current state, where the alignment is equal to .
- Step 4: The receptivity is modeled by using a classical sigmoidal function. The concept is that more alignment is considered receptivity:
- Step 5: The new state X and, therefore, the new epistemic state is given in accordance with expression (3):
- Step 6: The convergence is achieved; this means that the belief is reached if the norm of results to be less than a given threshold; otherwise, the procedure will start again from Step 2.
4. The Dialogic Approach in an Automatic Control Real Context
1-Luigi: The design of compensators for linear time-invariant control of SISO systems relies heavily on both experience and trial-and-error methods. This is a traditional engineering approach. What do you think about introducing decision-based support systems to speed up the design process and help practicing engineers achieve effective results more quickly?
Giuseppe: We could try to develop an Expert System to support your goal. In fact, we can formalize the acquired knowledge into a set of rules—both for selecting elementary networks and for choosing suitable parameters. The system could interface with MATLAB for numerical computation and verification, all within a trial-and-error framework. I can start building the knowledge base as you suggest.
2-Luigi: I’m very glad that you support my proposal. I’ll provide you with my design rules, and you can begin developing the system.
Giuseppe: Luigi, I’ve prepared the system and also included rules that allow us to design PID controllers and select their gains. The Expert System enables a dialog-based interaction where we can choose between PID controllers and cascaded elementary networks. I believe the system is ready for testing. Provide me with classical examples, and I’ll present both the system and the case studies to students.
3-Luigi: Welcome, Giuseppe. Involving more people will strengthen our project and help disseminate our knowledge. Next week, you could discuss the project with Peter—he has extensive experience in control design and could help us make the project more robust.
Giuseppe: Welcome, Peter.
Giuseppe: Peter, I’d like to introduce you to our Expert System, which integrates designer knowledge into the compensator design process, enabling rapid development. We’ve already proposed several examples, and the students have shown great interest.
Peter: I’m excited to work with you, Giuseppe, and to explore more examples together. The cases you’ve presented align with those found in classical control textbooks. However, I must point out that these texts often don’t clearly specify when a system can be compensated using a stable compensator, including the types you propose. Here’s an example: . Try this one, Giuseppe.
Giuseppe: Our system cannot find suitable networks for this case. This doesn’t mean the system is incorrect—it’s just incomplete.
Peter: Exactly. The system I provided lacks the PIP property and cannot be stabilized using elementary stable networks.
4-Luigi: Excellent point, Peter. We need to expand the knowledge base and deepen our understanding. What strategy do you suggest for approaching this issue?
Peter: We should discuss a general strategy for robust control during upcoming seminars. I’ll present my approach in detail then [18].
5-Luigi: Peter, your method assumes a well-known plant model and a mathematically derived compensator. What’s your view on using Fuzzy Logic for designing control compensators?
Peter: I don’t have enough expertise in Fuzzy Logic. I recommend exploring various fields to fully understand the problem and identify the most effective control strategy.
6-Luigi: I’ll try to contact Lofti Zadeh.
7-Luigi: Dear Lofti, I’m interested in evaluating multiple strategies for controller design, particularly involving Fuzzy Logic [19].
Lofti: Welcome, Luigi. I’m aware that a company is developing a Fuzzy Logic-based microcontroller that could be useful for your aims. The company is STMicroelectronics, located in your city. Contact Gianguido.
8-Luigi: Gianguido, I understand you’re coordinating a project on a Fuzzy Logic-based microcontroller. I’m eager to explore real-world applications of advanced control systems, and your work is of great interest to me.
Gianguido: Wonderful, Luigi. We’ll collaborate on this. The microcontroller is called WARP 1. I’ll introduce you to its capabilities.
9-Luigi: It’s a powerful microcontroller. I propose using it both for system modeling—based on process control expertise—and for implementing controllers derived from systems engineering. Even when a precise mathematical model is unavailable, we can build a fuzzy dynamic model using measurements and expert knowledge, enabling faster controller development.
Gianguido: Excellent idea, Luigi. The company finds this approach very promising. I should add that WARP 1 will be followed by WARP II. These are not conventional microcontrollers with software-based fuzzy logic—they use hardware-implemented fuzzy inference.
Lofti: Your approach is innovative and offers great potential for the control community. Keep going and develop further results.
10-Luigi: Gianguido, I had a meeting with researchers working on backpropagation. They introduced me to multilayer perceptrons and associative memory. It’s a fascinating area. I believe neural networks could be used for modeling, while WARP devices can handle control.
Gianguido: That sounds promising. But be cautious with learning algorithms—they can be numerically weak. Try using global optimization techniques to enhance them.
Matteo: To accelerate convergence during learning, we could use auxiliary neural networks to speed up the weight adjustment process. Therefore, we could couple the technique of learning with the dynamical prediction techniques, also based on neural network-based predictors. Therefore, Networks of Networks for learning.
11-Luigi: George, I’m working on neural networks for modeling, and I’m interested in robotics applications where quaternion-based modeling is relevant. Have you studied interpolation problems in the quaternion field?
George: That’s an excellent question, Luigi. So you’re trying to invent quaternion-based neural networks! […] I encourage you to follow your research about. I invite you also to consider using quaternion-based networks for hyperchaotic time series prediction [20].
12-Luigi: Leon, I’ve explained my research activities in system modeling and control. Do you have any suggestions?
Leon: Luigi, you started with analog controllers and have now reached complex AI-based systems. I recommend exploring Cellular Nonlinear Networks (CNNs). […]
Tamas: Your research is impressive, Luigi. I also see your interest in chaos control. I think you now have a great opportunity to integrate all these topics. Cellular Neural Networks architectures are similar to the Cellular Automata
13-Luigi: Thank you, my friends. Your encouragement has led me to talk with Gianguido about building a CNN-based microcontroller with a 128 × 128 array of analog cells. […]
Tamas and Leon: That would be fantastic!
14-Luigi: Gianguido, I propose developing the ACE 128 × 128. A CNN-based microcontroller could be a game-changer for distributed, emergent systems. […]
Gianguido: Let’s do it!
Mario: We’re organizing the project, the consortium, and the deliverables. Everything should be ready by 2002.
Leon and Tamas: The ACE device opens new frontiers. It can implement reaction-diffusion equations in hardware. […] [21].
15-Luigi: Your encouragement is vital. I’d like to share my latest insights. We’ve discovered that due to imperfections in analog electronic technology, each CNN cell is slightly different. […]
Henry: I fully agree. I recommend experimenting with MEG data to quickly demonstrate the practical impact [22].
16-Luigi: I propose involving Maide in this research. She could come to San Diego and possibly suggest further applications.
Leon, Lofti, Gianguido: That’s a great opportunity, Luigi. What are your new ideas?
17-Luigi: Leon invented CNNs, and Lofti introduced Fuzzy Logic. Gianguido has supported both hardware projects. My idea is to combine them—to develop a Fuzzy Logic-based CNN! […]
Leon: Why?
Lofti: Can we integrate our theories?
Gianguido: Designing the hardware won’t be straightforward. […] Start formalizing the architecture and begin new research.
18-Luigi: Many applications benefit from expert knowledge and would also leverage CNN-based architectures. […]
The following recently happened:Leon: Absolutely. Also, don’t forget about the memristor! […] Idea Luigi: Memristors based CNN!
19-Luigi: Can we undertake a systematic study of human-machine interface modeling? This is a timely and important topic. […]
Adriano: Absolutely. We can apply neural networks and dynamical systems theory. I also have an industrial robot in my lab that we can use as a basis for the study. I propose making this the subject of my PhD thesis!
20-Luigi: I suggest to link the subject to mathematical models.
- Luigi;
- Giuseppe;
- Peter;
- Lofti;
- Gianguido;
- Matteo;
- George;
- Leon;
- Tamas;
- Henry;
- Adriano;
- Maide;
- Mario.
5. The a Posteriori Answers Based on ChatGPT Maieutic Appoach
5.1. The First 20 Questions
- Q1
- Is the design of a control system based on experience?
- Q2
- Could we use expert systems to assist in the design of compensators?
- Q3
- I mean using expert systems to help select the elementary networks.
- Q4
- Yes, I mean selecting the lead-lag parameters with the help of expert systems.
- Q5
- Under which conditions can expert systems select the appropriate compensator?
- Q6
- That’s not entirely accurate. Some systems cannot be compensated using simple lead-lag networks.
- Q7
- I know that the double PIP property is required to choose a lead-lag network as a compensator.
- Q8
- Therefore, to design the expert system, we need a knowledge base that includes topics in robust control. That’s not entirely accurate. Some systems cannot be compensated using simple lead-lag networks.I know that the double PIP property is required to choose a lead-lag network as a compensator. Therefore, to design the expert system, we need a knowledge base that includes topics in robust control.
- Q9
- Could I have a discussion with Prof. Zadeh to get suggestions on incorporating fuzzy concepts into my expert system for compensator design?
- Q10
- I understand. Moreover, I need a fast controller that can handle more detailed process information. How can this be practically implemented?
- Q11
- Dear Prof. Zadeh, I will speak with Dr. Gianguido Rizzotto about the possibility of designing a fuzzy controller platform.
- Q12
- The project we developed is based on the WARP 1 fuzzy microcontroller. Are you familiar with it?
- Q13
- Very good. Are you also familiar with the WARP 2 device?
- Q14
- Ideally, I want a system that can both identify a fuzzy model and generate a fuzzy controller to ensure desired closed-loop performance. Can the WARP 2 handle this?
- Q15
- Indeed, the problem is easier to manage if process control specialists are involved in the controller design. But what can I do if they are not?
- Q16
- Does this mean using neural networks for system identification?
- Q17
- That’s a good idea. However, isn’t the backpropagation algorithm poorly conditioned for learning?
- Q18
- Good point. Additionally, I have an idea: using global optimization algorithms to overcome the drawbacks you mentioned.
- Q19
- Using a classical multilayer perceptron introduces some issues. I’m considering extending the theory to complex and quaternion-based networks. What’s your opinion?
- Q20
- I would like to propose using quaternion-based networks for both system identification and controller implementation.
- Q21
- Indeed, this approach should ultimately be implemented on digital systems. But I’m also curious—what about implementation using analog systems?
5.2. GPT Answers
- A1
- Is the design of a control system based on experience?Yes, in many practical scenarios, control system design often relies on the engineer’s experience and intuition. Classical control design techniques like tuning PID or lead-lag compensators have traditionally involved trial-and-error or heuristic methods developed through accumulated expertise.
- A2–4
- Could expert systems assist in the design of compensators, particularly in selecting elementary networks and lead-lag parameters?Absolutely. Expert systems can encapsulate design heuristics and rules derived from expert knowledge to help automate compensator design. For example, an expert system could analyze system characteristics and recommend lead-lag parameters based on a knowledge base of control principles and prior designs.
- A5–7
- Under what conditions can expert systems select the appropriate compensator?Expert systems can effectively select compensators when the design problem matches the assumptions embedded in their knowledge base. For instance, the classic lead-lag network is suitable when the system satisfies properties like the Parity Interlacing Property (PIP) property. If the system doesn’t meet these conditions, simpler compensators may not suffice.
- A8
- Importance of robust control knowledge baseTo design a competent expert system, the knowledge base must cover advanced control concepts, including robust control. This allows the system to handle uncertainties and more complex dynamics, extending beyond simple compensator selection.
- A9–11
- Incorporating fuzzy concepts and fast controllersDiscussing with experts like Prof. Zadeh is a great step for integrating fuzzy logic into the compensator design process. Fuzzy controllers can handle uncertainties and nonlinearities better, and platforms like the WARP 1 fuzzy microcontroller provide practical hardware implementation. This leads to fast controllers that process detailed information effectively.
- A12–14
- Familiarity with WARP devices and fuzzy modelingThe WARP 1 device is a known fuzzy microcontroller platform; WARP 2 offers improvements and could support both fuzzy model identification and controller generation, providing an integrated solution for robust closed-loop performance.
- A15
- What if process control specialists are unavailable?When specialists are not accessible, automated design tools—combining expert systems, fuzzy logic, and machine learning—can help bridge the gap by embedding expert knowledge and adaptive algorithms.
- A16–18
- Neural networks and learning challengesNeural networks are indeed promising for system identification, but classical algorithms like backpropagation can struggle with convergence and conditioning. Incorporating global optimization methods can help avoid local minima and improve learning robustness.
- A19–20
- Extending neural networks with complex and quaternion-based approachesExtending theory to complex and quaternion-valued neural networks is an exciting frontier. These can naturally handle multidimensional signals and rotational symmetries, offering potentially more efficient and richer representations for system identification and control.
- A21
- Implementation on digital vs. analog systemsWhile digital implementation is dominant due to flexibility and scalability, analog systems still hold interest for ultra-fast or low-power applications. Exploring analog or hybrid architectures for these advanced controllers could open new possibilities.If you’d like, I can help you develop detailed explanations or draft specific questions or proposals for your discussions with Prof. Zadeh or Dr. Rizzotto on fuzzy and neural control systems. Would that be helpful?
5.3. Second Part GPT Questions and ChatGPT Answers
Question 1: I was just discussing the possibilities of implementing control for complex systems using analog processors.
GPT: That’s a very timely topic—analog processors, especially when designed for parallel computation, offer significant advantages in speed and energy efficiency for real-time control of complex, nonlinear systems.
Question 2.: What would you suggest?
GPT: I suggest exploring hybrid analog–digital architectures. Analog processors can handle continuous-time dynamics efficiently, while digital components can manage high-level logic and long-term adaptation.
Question 3.: What is your opinion on Cellular Nonlinear Networks (CNNs)?
GPT: CNNs are a powerful paradigm for distributed, parallel processing. Their local connectivity and nonlinear dynamics make them ideal for implementing spatiotemporal control laws, especially in systems requiring real-time response.
Question 4.: But what is your opinion on the role of this approach?
GPT: I believe CNNs represent a foundational approach for emergent control. Their role is especially important in modeling systems where global behavior arises from local interactions, such as swarm robotics or distributed sensor networks.
Question 5.: What is your opinion on the ACE device?
GPT: The ACE (Analogic Cellular Engine) device is a landmark in analog VLSI computing. It demonstrates the practical viability of CNN-based processing for applications like image processing and edge detection at high speeds and low power consumption.
Question 6.: What has Luigi Fortuna contributed to the field of CNNs?
GPT: Luigi Fortuna has made substantial contributions, particularly in extending CNN theory to practical applications. His work has bridged the gap between nonlinear dynamics, analog computing, and control, pushing forward real-world implementations of CNNs.
Question 7.: Did you know that the ACE 128 × 128 was implemented by STMicroelectronics?
GPT: Yes, that implementation was significant—it showed that industrial-scale fabrication of CNN-based processors was feasible. It also validated CNN hardware in real-world signal processing tasks.
Question 8.: What is your opinion on the potential of designing controllers based on CNNs?
GPT: I think there is great potential, especially for embedded, real-time systems where fast, distributed decision-making is crucial. CNNs could form the backbone of adaptive and decentralized controllers, particularly in fields like robotics and autonomous systems.
Question 9.: Lotfi Zadeh, Leon Chua, and Luigi Fortuna are discussing their joint research. What is the topic?
GPT: They are most likely discussing the convergence of fuzzy logic, nonlinear dynamics, and cellular architectures—specifically, Cellular Nonlinear Fuzzy Networks.
Question 10.: I’ll give you the correct answer: they are discussing Cellular Nonlinear Fuzzy Networks!
GPT: That makes perfect sense. Cellular Nonlinear Fuzzy Networks combine the strengths of fuzzy inference with the structural efficiency of CNNs, enabling flexible yet localized decision-making.
Question 11.: Fuzzy Cellular Nonlinear Networks are distributed, locally connected architectures in which each cell is represented by a dynamical system governed by fuzzy rules.
GPT: Exactly. This architecture allows for adaptive control with high fault tolerance, ideal for systems with uncertain, nonlinear, or time-varying dynamics.
Question 12.: Therefore, the concept of emergent control for distributed systems arises.
GPT: Indeed. Emergent control leverages local rules and interactions to produce globally coherent behavior—a hallmark of many natural and engineered systems.
Question 13.: But what is your opinion on brain-based control architectures?
GPT: They are not only fascinating but increasingly practical. Brain-based architectures offer models for distributed, adaptive, and robust control strategies, drawing inspiration from neurodynamics, plasticity, and hierarchical organization.
Question 14.: Indeed, there is a clear coherence between distributed emergent control and principles of brain function.
GPT: Yes, both rely on decentralized processing, local feedback, and adaptive learning—principles that enable resilience and flexibility.
Question 15.: Today, we have the possibility of using Brain-Computer Interfaces (BCIs). What do you think about that?
GPT: BCIs open a transformative pathway for control systems. They enable direct integration between neural signals and engineered systems, which could revolutionize fields like assistive robotics, prosthetics, and cognitive automation.
Question 16.: This represents a crucial link between brain engineering and advanced control systems.
GPT: Absolutely. The feedback loop between neural intent and machine execution is a frontier for both neuroscience and control engineering.
Question 17.: Moreover, the modeling and control of human-machine systems is a highly relevant topic today.
GPT: It’s central to modern cyber-physical systems. As machines become more integrated into daily life, modeling the dynamics of human-machine interaction becomes critical for safety, performance, and user experience.
Question 18.: Essentially, the models are relatively simple—such as in human car-driving control.
GPT: True. In some cases, simple models suffice, but even these can exhibit complex behaviors when feedback, delays, and environmental uncertainty are included.
Question 19.: In my opinion, modeling such systems requires time-delay theory and accurate knowledge of the actual feedback parameters. What do you think?
GPT: I agree. Time delays and feedback loops are central to accurately modeling human-in-the-loop systems. Without accounting for them, models may fail to predict key dynamics like instability or overcorrection.
Question 20.: In your opinion, what are the future perspectives in this area?
GPT: Future perspectives include adaptive control informed by neurocognitive data, closed-loop BCI-driven systems, and analog-digital hybrid architectures capable of learning from sparse, noisy inputs.
Question 21.: That’s not a satisfactory answer—I was referring to real-world applications.
GPT: Understood. Real-world applications include adaptive exoskeletons, autonomous vehicles with human override systems, intelligent neuroprosthetics, and haptic-feedback surgical robots.
Question 22.: That’s a better answer now. I would also add surgical robots as an example.
GPT: Absolutely—surgical robots are a key example where high-precision control, real-time feedback, and human intent interpretation converge.
5.4. Summary of the Perceived Results
- 0.3–0.5 sufficient;
- 0.5–0.7 good;
- 0.7–0.9 very good.
6. Conclusions
Author Contributions
Funding
Conflicts of Interest
Appendix A. ChatGPT Research Proposal
Applying Maieutic Dialogue to Enhance Conceptual Learning in Control Engineering Education
- 1.
- Introduction
- 2.
- Objectives
- Design an intelligent tutor or simulation interface using Socratic questioning (maieutic dialogue).
- Implement this system for selected control topics (e.g., PID tuning, Bode plots, state-space design).
- Compare learning outcomes of students using the maieutic system vs. traditional methods.
- Evaluate engagement, retention, and error diagnosis capabilities of the maieutic method.
- 3.
- Literature Review (Summary)
- Maieutic Teaching Methods: Used in law, philosophy, and medicine, underutilized in engineering.
- Control Systems Education: Focuses on math rigor; lacks reflective thinking approaches.
- Intelligent Tutoring Systems (ITS): Few systems incorporate maieutic question loops in engineering.
- 4.
- Methodology
- 5.
- Expected Outcomes
- Improved conceptual grasp of control topics.
- Better articulation of reasoning and error diagnosis.
- Higher engagement and reflective thinking.
- Model for hybrid AI-assisted engineering education.
- 6.
- Tools and Technologies
Component | Tool |
Simulation engine | MATLAB or Python Control |
Dialogue system | GPT API, LangChain |
Interface | React/Flask or MATLAB GUI |
Assessment tools | Google Forms, Jupyter, SPSS |
- 7.
- Timeline (6-Month Example)
Month | Task |
1 | Literature review, planning |
2 | Prototype development |
3 | Question logic and refinement |
4 | Pilot study |
5 | Full experiment and analysis |
6 | Report writing and publication |
- 8.
- Challenges and Limitations
- Student bias toward passive learning;
- Need for advanced NLP capability;
- Balancing question difficulty;
- Generalizability concerns.
- 9.
- References (Suggestions)
- 10.
- Potential for Future Work
- Apply to other engineering fields;
- Integration with AR/VR labs;
- Deeper GPT integration for live tutoring.
References
- Casti, J.L. The Cambridge Quintet: A Work of Scientific Speculation; Perseus Books: New York, NY, USA, 1998. [Google Scholar]
- Tononi, G. Phi: A Voyage from the Brain to the Soul; Pantheon: Rome, Italy, 2012. [Google Scholar]
- Haddad, W.M.; Chellaboina, V. Nonlinear Dynamical Systems and Control: A Lyapunov-Based Approach; Princeton University Press: Princeton, NJ, USA, 2011. [Google Scholar]
- Zadeh, L.A.; Desoer, C.A. Linear System Theory: The State Space Approach; Courier Dover Publications: Mineola, NY, USA, 2008. [Google Scholar]
- Willems, J.C.; Polderman, J.W. Introduction to Mathematical Systems Theory: A Behavioral Approach; Springer: Berlin/Heidelberg, Germany, 1997. [Google Scholar]
- Terman, F.E. Radio Engineering; McGraw-Hill: New York, NY, USA, 1947. [Google Scholar]
- Levine, W.S. The Control Handbook (Three Volume Set); CRC Press: Boca Raton, FL, USA, 2018. [Google Scholar]
- Cooper, J.M. Plato’s Theaetetus; Routledge: Abingdon, UK, 2015. [Google Scholar]
- Leigh, F. Platonic Dialogue, Maieutic Method and Critical Thinking. J. Philos. Educ. 2007, 41, 309–323. [Google Scholar] [CrossRef]
- Freire, P. Pedagogy of Hope; Bloomsbury Academic: London, UK, 2021. [Google Scholar]
- Kline, N. Time to Think: Listening to Ignite the Human Mind; Hachette: London, UK, 1999. [Google Scholar]
- Stanier, M.B. The Coaching Habit: Say Less, Ask More & Change the Way You Lead Forever; Box of Crayons Press: Toronto, ON, Canada, 2016. [Google Scholar]
- Rogers, C.R. Becoming a Person. In Proceedings of the Symposium on Emotional Development, Oberlin, OH, USA, 7–9 April 1957; Association Press: New York, NY, USA, 1957. [Google Scholar]
- Longo, A. Danilo Dolci: Environmental Education and Empowerment; Springer International Publishing: Berlin/Heidelberg, Germany, 2020. [Google Scholar]
- Boethius, A.; Goins, S. The Consolation of Philosophy: With an Introduction and Contemporary Criticism; Ignatius Press: San Francisco, CA, USA, 2011. [Google Scholar]
- Manca, V. Conversazioni Artificiali. La Maieutica al Tempo dei Chatbot; Carte Amaranto: Pontremoli, Italy, 2024. [Google Scholar]
- Li, W.; Shen, Z.; Liu, X.; Ding, C.; Shen, J. Fed-OGD: Mitigating Straggler Effects in Federated Learning via Orthogonal Gradient Descent. IEEE Trans. Comput. 2025, 74, 3018–3031. [Google Scholar] [CrossRef]
- Dorato, P.; Fortuna, L.; Muscato, G. Robust Control for Unstructured Perturbations—An Introduction; Springer: Berlin/Heidelberg, Germany, 1992. [Google Scholar]
- Zadeh, L.A. Is There a Need for Fuzzy Logic? Inf. Sci. 2008, 178, 2751–2779. [Google Scholar] [CrossRef]
- Cybenko, G. Approximation by Superpositions of a Sigmoidal Function. Math. Control Signals Syst. 1989, 2, 303–314. [Google Scholar] [CrossRef]
- Chua, L.O.; Roska, T. Cellular Neural Networks and Visual Computing: Foundations and Applications; Cambridge University Press: Cambridge, UK, 2002. [Google Scholar]
- Abarbanel, H.D.I. Analysis of Observed Chaotic Data; Springer: Berlin/Heidelberg, Germany, 2012. [Google Scholar]
- Fortuna, L.; Buscarino, A. The Impact of Circuits and Systems on the Etna Valley Site [CAS Regional Report]. IEEE Circuits Syst. Mag. 2024, 24, 98–100. [Google Scholar] [CrossRef]
- Haque, M.A.; Li, S. Exploring ChatGPT and its Impact on Society. AI Ethics 2025, 5, 791–803. [Google Scholar] [CrossRef]
- Eysenbach, G. The Role of ChatGPT, Generative Language Models, and Artificial Intelligence in Medical Education: A Conversation with ChatGPT and a Call for Papers. JMIR Med. Educ. 2023, 9, e46885. [Google Scholar] [CrossRef] [PubMed]
- Nof, S.Y. (Ed.) Springer Handbook of Automation, 2nd ed.; Springer Handbooks; Springer: Cham, Switzerland, 2023; pp. LII, 1536. [Google Scholar] [CrossRef]
- Li, W.; Chen, J.; Wang, Z.; Shen, Z.; Ma, C.; Cui, X. IFL-GAN: Improved Federated Learning Generative Adversarial Network with Maximum Mean Discrepancy Model Aggregation. IEEE Trans. Neural Netw. Learn. Syst. 2023, 34, 10502–10515. [Google Scholar] [CrossRef]
- Li, W.; Gu, C.; Chen, J.; Ma, C.; Zhang, X.; Chen, B.; Wan, S. DLS-GAN: Generative Adversarial Nets for Defect Location Sensitive Data Augmentation. IEEE Trans. Autom. Sci. Eng. 2023, 21, 5173–5189. [Google Scholar] [CrossRef]
- Paul, R.; Elder, L. Critical thinking: The nature of critical and creative thought. J. Dev. Educ. 2006, 30, 34. [Google Scholar]
- Ogata, K. Modern Control Engineering, 5th ed.; Prentice Hall: Upper Saddle River, NJ, USA, 2010. [Google Scholar]
- Bishop, R.H.; Dorf, R.C. Teaching modern control system design. In Proceedings of the 38th IEEE Conference on Decision and Control, Phoenix, AZ, USA, 7–10 December 1999; Volume 1, pp. 364–369. [Google Scholar] [CrossRef]
- VanLehn, K. The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems. Educ. Psychol. 2011, 46, 197–221. [Google Scholar] [CrossRef]
- Koedinger, K.R.; Aleven, V. Exploring the assistance dilemma in experiments with cognitive tutors. Educ. Psychol. Rev. 2007, 19, 239–264. [Google Scholar] [CrossRef]
- Bateson, N.; Guddemi, P. Systems, Tools, and Bateson’s Cybernetics: A Joint Metalogue. In Traditions of Systems Theory; Arnold, D.P., Ed.; Routledge: Abingdon, UK, 2013; pp. 345–362. [Google Scholar]
Question | Sufficient | Good | Very Good |
---|---|---|---|
Q1 | x | ||
Q2 | x | ||
Q3 | x | ||
Q4 | x | ||
Q5 | x | ||
Q6 | x | ||
Q7 | x | ||
Q8 | x | ||
Q9 | x | ||
Q10 | x | ||
Q11 | x | ||
Q12 | x | ||
Q13 | x | ||
Q14 | x | ||
Q15 | x | ||
Q16 | x | ||
Q17 | x | ||
Q18 | x | ||
Q19 | x | ||
Q20 | x | ||
Q21 | x | ||
Q22 | x |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Fortuna, L.; Scibilia, A. Maieutic, Natural, and Artificial Forms in Automatic Control Case Study. Information 2025, 16, 761. https://doi.org/10.3390/info16090761
Fortuna L, Scibilia A. Maieutic, Natural, and Artificial Forms in Automatic Control Case Study. Information. 2025; 16(9):761. https://doi.org/10.3390/info16090761
Chicago/Turabian StyleFortuna, Luigi, and Adriano Scibilia. 2025. "Maieutic, Natural, and Artificial Forms in Automatic Control Case Study" Information 16, no. 9: 761. https://doi.org/10.3390/info16090761
APA StyleFortuna, L., & Scibilia, A. (2025). Maieutic, Natural, and Artificial Forms in Automatic Control Case Study. Information, 16(9), 761. https://doi.org/10.3390/info16090761