After studying various aspects of the general theory of information, to me, it is becoming clear that as individuals, we view the material world that we interact with a mental model that has evolved over our lifetime using the autopoietic and cognitive processes that we have both inherited and learned. This explains why we individually react differently to the same observations of external reality. The difference in our reactions is proportional to the knowledge gap. As we interact with each other, we tend to either reduce or increase this knowledge gap and based on external reality, this could lead to severe consequences depending on the actions we take based on our knowledge.
The problem of increased knowledge gap between actors interacting with each other is exaggerated by the rapid changes and large fluctuations both in how the external world is evolving and the resulting explosion of knowledge required to keep up with these changes. According to Prigogine, large fluctuations could result in the emergence of new structures due to internal self-reorganization. However, the self-organization resulting from emergence is unpredictable. This is because the process is nonlinear and depends on a multitude of factors, including the initial conditions and the nature of the fluctuations. Understanding the impact of fluctuations on these structures could potentially lead to more robust and adaptable algorithms.
In fact, biological systems have developed a unique ability to maintain the identity of their structures, observe themselves and their interactions with the external world using information processing structures, and make sense of what they are observing fast enough to do something about it while they are still observing it. They have gone beyond self-organization to self-regulation by reducing the knowledge gap between external reality and their internal model of reality.
How can we extend this capability to actors interacting with each other and the external world to reduce the knowledge gap between them in real-time? This requires access to the same information by all the actors interacting with each other. Each actor has the access to the “known knowns” through personal knowledge they have acquired through their lifetime. However, they do not have access to the “unknown” to them but are “known” to others. It is a lot of effort to determine what is known to others but is not known to you especially, if there are rapid changes areas that you are not aware but impact what you know. When external reality is changing rapidly, the need for access to unknown knowns becomes more important.
The Large Language models using Deep learning provide knowledge representation through learning – the automated formation of useful representations from data. It is now accessible in real-time through various offerings in the form of Bing Chat, Bard, ChatGPT, etc. Individuals can use access to the common knowledge pool using various tools and individuals can search for the unknown knowns before they make critical judgment or important decision.
Here is an example I used to update my knowledge using Bing Chat.
How do humans learn using information from the material world as observers with unique identities?
## Bing
Humans learn by interacting with the material world and processing information based on their unique identities and experiences. Here’s a breakdown of the process:
– Encountering New Information: Learning begins when we encounter new information from our environment. This could be through reading, listening, observing, or hands-on experiences.
– Active Processing: Learning is an active process that involves paying attention to the new information, coordinating it with what we already know, storing it in our memory, and applying it. For instance, when reviewing lecture notes, we may make new connections among concepts, recognize the significance of some information we hadn’t grasped before, anticipate how we will be tested, or ask ourselves new questions about the material.
– Effortful Learning: Research shows that effortful learning usually signals not only deeper learning, but more durable long-lasting knowledge. It’s analogous to weight training. Investing more effort in grappling with new information builds stronger, deeper knowledge.
– Spaced Repetition: The spaced repetition of information is crucial for memory. Revisiting the learned material after a certain period helps in better retention of the information.
– Learning from Experience: Learning also occurs as a result of experience. Once we’ve tried a technique or a method, we can determine whether it works for us and then use it in the future.
– Influence of Identity: Our unique identities and experiences can influence how we interpret and understand information. This can shape our attitudes, knowledge, and behavior.
– Neural Adaptation: On a biological level, learning involves changes in the brain’s neural networks. When two neurons fire together, the connections between them—the synapses—grow stronger, indicating that learning has taken place.
Remember, learning is a lifelong process that continues beyond formal education and takes place throughout our lives.
Source(s)
1. What Is Learning? – Verywell Mind
2. How People Learn: Common Beliefs Vs. Research
3. How we learn: the secret to all learning & human development
4. The Brain Learns in Unexpected Ways | Scientific American
5. What Is the Psychology of Learning? – Verywell Mind
How do machines learn from the information from the material world without a unique identity and as they are fed data from the material world?
## Bing
Machines learn from data using a process called machine learning, which is a subset of artificial intelligence. Unlike humans, machines don’t have unique identities or subjective experiences. Instead, they learn by recognizing patterns in the data they are fed and making predictions based on those patterns. Here’s a simplified explanation of how machines learn:
– Data Input: Machines are fed data, which could be anything from images and text to numerical data.
– Learning Algorithms: Machines use learning algorithms to process the data. These algorithms are designed to recognize patterns and learn from them. There are three main types of machine learning algorithms: supervised learning, unsupervised learning, and reinforcement learning.
– Supervised Learning: In supervised learning, the machine is given input data along with the correct output. The goal is to learn a general rule that maps inputs to outputs.
– Unsupervised Learning: In unsupervised learning, the machine is given input data without any corresponding output data. The goal is to find patterns and structure in the input data.
– Reinforcement Learning: In reinforcement learning, the machine learns to make decisions by performing certain actions and receiving rewards or penalties.
– Model Training: The machine learning model is trained on a portion of the data, learning to recognize patterns and make predictions.
– Model Testing: The trained model is then tested on a different portion of the data to see how well it can make predictions.
– Prediction: Once the model is trained and tested, it can make predictions on new data.
– Continuous Learning: Machine learning models can continue to learn and improve over time as they are exposed to more data.
It’s important to note that while machines can learn from data, they don’t understand the data in the same way humans do. They don’t have consciousness or subjective experiences. They simply process data and make predictions based on patterns.
Source(s)
1. How Do Machines Learn? A Beginners Guide – Levity
2. Machine learning, explained | MIT Sloan
3. How Does A Machine Learn? – Forbes
4. Machine Learning | What Is Machine Learning? | Introduction To Machine Learning | 2021 | Simplilearn
5. Machine Learning Explained in 100 Seconds
6. What is Machine Learning? | Machine Learning Basics | Machine Learning Tutorial | Edureka
7. What Is Machine Learning? | A Beginner’s Guide – Scribbr
8. What Is Machine Learning? – MATLAB & Simulink – MathWorks
What are the autopoietic and cognitive behaviors of humans?
## Bing
Autopoietic behavior refers to the self-producing and self-maintaining nature of living systems. This concept was introduced by Chilean biologists Humberto Maturana and Francisco Varela to define the self-maintaining chemistry of living cells. Autopoiesis enables living beings to use the specification in their genomes to instantiate themselves using matter and energy transformations. They reproduce, replicate, and manage their stability. An autopoietic system is capable of producing and maintaining itself by creating its own parts.
On the other hand, cognitive behavior refers to the actions of obtaining and using knowledge. It is concerned with how information is learned and passed on, as well as the creative application of knowledge and personal beliefs. Cognitive psychology involves the study of internal mental processes—all of the workings inside your brain, including perception, thinking, memory, attention, language, problem-solving, and learning. It concerns how we take in information from the outside world, and how we make sense of that information. Cognitive behavior accounts for actions of obtaining and using knowledge.
It’s important to note that while these behaviors are distinct, they are interconnected. Autopoiesis provides the biological basis for life, while cognition allows for the processing and application of information, enabling complex behaviors and interactions with the environment.
Source(s)
2. BDCC | Free Full-Text | Infusing Autopoietic and Cognitive Behaviors …
4. Cognitive Psychology: The Science of How We Think – Verywell Mind
6. Cognitive Approach In Psychology
7. Autopoiesis, biological autonomy and the process view of life – Springer
8. A New Class of Autopoietic and Cognitive Machines – MDPI
9. A New Class of Autopoietic and Cognitive Machines
10. Cognition | Psychology Today
11. en.wikipedia.org
Can machines be infused with an identity and knowledge usng a digital genome to mimic autopoietic and cognitive behaviors?
## Bing
The idea of infusing machines with autopoietic and cognitive behaviors to mimic living organisms has been a topic of interest in the field of artificial intelligence. However, current AI technologies fall short of replicating even the basic autopoietic and cognitive behaviors found in primitive biological systems.
To make machines mimic living organisms, they must be infused with autopoietic and cognitive behaviors. This involves creating a system that can replicate itself and maintain identity and stability while facing fluctuations caused by external influences. Cognitive behaviors would allow the system to model its state, sense internal and external changes, analyze, predict, and take action to mitigate any risk to its functional fulfillment.
The knowledge obtained from different mechanisms is integrated with a common knowledge representation and is used to manage the system’s structure and dynamics with autopoietic and cognitive behaviors. This approach is analogous to how the neocortex repurposed the reptilian brain and paves the path for digital machines to mimic living organisms using an integrated knowledge representation from different sources.
However, it’s important to note that while machines can be programmed to mimic certain behaviors, they do not possess consciousness or subjective experiences. They simply process data and make predictions based on patterns. Therefore, while machines can exhibit behaviors that mimic autopoiesis and cognition, they do not truly possess these qualities in the way that living organisms do.
Source(s)
1. A New Class of Autopoietic and Cognitive Machines – MDPI
2. BDCC | Free Full-Text | Infusing Autopoietic and Cognitive Behaviors …
3. A New Class of Autopoietic and Cognitive Machines
4. Infusing Autopoietic and Cognitive Behaviors into Digital Automata to …
5. https://doi.org/10.3390/info13010024
6. https://doi.org/10.3390/bdcc6010007
Could such autopoietic and cognitive machines be treated as extensions of human capabilities that augment human capabilities by updating knowledge in real-time and assist in predicting and acting in real-time with updated knowledge?
## Bing
Yes, autopoietic and cognitive machines could potentially be treated as extensions of human capabilities. These machines, by updating their knowledge in real-time, can assist in predicting and acting in real-time with updated knowledge.
Such machines can augment human capabilities in several ways:
– Real-time Decision Making: These machines can analyze large amounts of data quickly and make real-time decisions based on that data.
– Predictive Analysis: They can use past data to predict future trends, which can be particularly useful in fields like finance, healthcare, and marketing.
– Automation: These machines can automate routine tasks, freeing up humans to focus on more complex tasks.
– Personalization: They can provide personalized recommendations based on individual preferences and behaviors.
However, it’s important to note that while these machines can mimic certain behaviors, they do not possess consciousness or subjective experiences. They simply process data and make predictions based on patterns. Therefore, while they can augment human capabilities, they are not replacements for human judgment and decision-making.
Source(s)
1. A New Class of Autopoietic and Cognitive Machines – MDPI
2. A New Class of Autopoietic and Cognitive Machines – MDPI
3. A New Class of Autopoietic and Cognitive Machines
4. A New Class of Autopoietic and Cognitive Machines – ResearchGate
5. https://doi.org/10.3390/info13010024
What I learned from this exercise is that I can update my knowledge based on information I did not have but others have, and the unknown knowns impact my model of my interactions with the external world, and potentially can change how I act. I can update my knowledge faster with LLMs than without them. As far the veracity, it is my current knowledge that determines whether I update my knowledge with new information or reject it. I will have to live with my decision.
C’est la vie.
I close this post with this quote from a Zen Master
Before I had studied Zen for thirty years,
I saw mountains as mountains,
and waters as waters.
When I arrived at a more intimate knowledge, I came to the point where I saw that mountains are not mountains,
and waters are not waters.
But now that I have got its very substance
I am at rest.
For it’s just that
I see mountains once again as mountains,
and waters once again as waters.
Bing
Here are some quotes from great masters on information, knowledge, intelligence, and wisdom:
- “The only true wisdom is in knowing you know nothing.” – Socrates
- “Knowledge is having the right answers. Intelligence is asking the right questions. Wisdom is knowing when to ask the right questions.” – Unknown
- “The measure of intelligence is the ability to change.” – Albert Einstein
- “Intelligence is the door to freedom and alert attention is the mother of intelligence.” – Jon Kabat-Zinn
- “Knowing yourself is the beginning of all wisdom.” – Aristotle
