Neuroscience - ToFeliz

Luciano Fagundes

Neurocomputing – Conclusion Paper

National Institute of Space Research

(*) Translated to English by ChatGpt4

Abstract

In this work, we will use the current knowledge of neural networks and psychoanalysis to propose the path to be taken to evolve Artificial Intelligence (AI) and achieve the development of Artificial Consciousness (AC). AI has been primarily based on the neural structures found in the human brain, which has led to a tremendous leap in the ability of computers to process and respond to questions. This research aims to take a step further. We attempt to propose a new structure for networks to include psychoanalytic concepts in their topology. We propose a new line of reasoning for the development of responses, incorporating control mechanisms, feelings, and subjectivity into the networks. All this is done by applying concepts theorized by psychoanalysis to explain the high-level functioning of human consciousness, without adhering specifically to any one neural structure.

Keywords: Artificial Intelligence, Artificial Consciousness, Neural Networks, Psychoanalysis, Human Brain, Cognitive Development, Subjectivity, Control Mechanisms, Reasoning Structure

Introduction

This article arises from reflections on neural networks, psychoanalytic structures, and some famous “failures” found in the results of Neural Networks.

Neural networks are mathematical mechanisms that can connect any input to any output. If we abstract this concept, it is as if, during training, we were searching for a dimension where all questions and answers align. The weight changes during training and various topologies do nothing but find a dimension (training result) where the answers to our questions are located. Even more interesting, they identify the most probable answers to questions that have not yet been asked (network generalization).

However, blindly trusting the neural network and its training seems unfinished to me. Always seeking a parallel with the human brain, there are control mechanisms likely running within the neural network, but operating separately. There must be some short-term memory system that allows reasoning, inference of the external world, and other processes. These mechanisms are not referenced in current neural networks.

Perhaps one of the main issues we face today with neural networks is how to express reasoning regarding a response. For example, if we take an LLM (Large Language Model) network and ask how to decorate a living room, it will respond by describing what objects to place, how to arrange them, etc. If we ask how it arrived at that response, it will mention a particular technique, such as lighting or design elements. But if we analyze the two responses, we find no clear line of reasoning from nothing to the final answer. Both the response and the explanation might not even be connected—they are simply outputs from a dimension found during training, which, aside from some randomness in the seed of the question, would always be the same in all cases. The network did not explain how it arrived at the answer; it only gave what a person might have said when asked how they arrived at the response. This may seem circular and confusing, but that’s precisely the point.

There is a classic example where the neural network arrived at the “correct” answer by the wrong path but failed to generalize and respond appropriately to real-world examples. This was the case of classifying a dog and a wolf [GEIRHOS1]. In this case, several labeled photos of wolves and dogs were shown to the network. The neural network ended up learning that the background of the photo was what defined whether it was a dog or a wolf. If the background was wild—snow, forest, etc.—it was a wolf. If it was a sofa, garden, or living room, it was a dog. As a result, the network gave grossly incorrect answers when presented with photos of dogs and wolves outside the training set. The AI could not explain what it was considering to solve the problem; humans identified the issue through trial and error, deducing the root of the training problem.

This is where psychoanalysis comes in. Today’s neural networks seem very focused on the brain as a question-answering machine. Psychoanalytic theory offers a broader abstraction and attempts to theorize about the internal components of the brain—not in terms of neural structures, but in terms of control structures that enable the brain to interact with the world. While psychoanalysis focuses on traumas and failures that occur during the formation of these structures, in our case, it is worth understanding how these abstractions “should” function, so we can restructure our neural network topologies accordingly.

Freud and the Psychic Apparatus

Freud proposed the psychic apparatus in 1900 [FREUD1], initially concerned with dream interpretation. For him, the psychic apparatus consisted of a sequence of steps, resembling a comb. On one side was the conscious, linked to all body sensors—skin, stomach, eyes, etc.—and the motor part. Freud viewed this apparatus as something akin to a neural network, with sensory inputs passing through intermediate layers and returning “motor” commands. For example, if a lion appears in front of you, the information enters through the eyes, passes through the neural network, and returns a command to your leg muscles, making you run.

The inner teeth of this comb represent the layers of our neural networks, processing the data, understanding it, and finding the appropriate response. Learning would occur through repetition and reward: each time an action succeeds, the same neurons are activated, strengthening that area and making that “memory” permanent. This is very close to current neural network training theories.

The most important aspect of this model is Freud’s first mention of the unconscious. That is, a significant portion of the brain’s neuron layers is hidden, and it is impossible to identify all factors influencing the generation of a response.

Lacan and the Brain as Language

Another prominent psychoanalyst was Jacques Lacan, who sought to formalize Freud’s theory mathematically. Perhaps his most important contribution was recognizing that the unconscious described by Freud was organized like a language [LACAN1].

This opens the door for us to imagine neural networks that communicate with each other through language—not only by neuron activation but through internal “conversation” in a language that could be translated into human language. We could have a neural network responsible for threat detection, whose output might not be mere probabilistic values between zero and one but could also be a phrase such as “I think there is a lion behind that tree.” In other words, the outputs of the networks could consist of commands and linguistic observations, translatable and understandable to humans.

The major advantage of representing the artificial “unconscious” as a language would be the emergence of a line of thought. If each internal structure has a linguistic output, we could maintain a log of these artificial “thoughts” and perceptions, comparing them with the final result.

Ego, Superego, and Id (Unconscious)

In Freud’s second topography, he advances the psychic apparatus by introducing the concepts of Ego, Superego, and Id. At this point, abstraction progresses further. Freud realized we need more than a simple question-answer neural structure. If this were enough, everyone would be the same; starting with a blank brain (a clean neural network) and training it the same way would yield identical neural networks. But we know this is not true for neural networks, much less for humans.

The Ego [FREUD2] is responsible for the survival of the individual, receiving external perceptions, comparing them with internal needs, and acting. To find balance, the Ego requires assistance from two other controllers, the Superego and the Id.

The Superego consists of all the rules acquired during life—what is allowed or not by law, guilt, etc. It serves as the Ego’s legal advisor. For example, if the Ego is hungry, sees a hot dog cart but lacks money, it asks the Superego, “Can I take the hot dog?” The Superego responds with something like, “If you do that, you could go to jail because you can’t pay.” This is a consultation because the Ego will make the final decision. The hunger may be so severe that the individual risks their health, leading the Id (unconscious) to say, “Eat or die!” The individual may then commit a crime to survive.

The Id or Unconscious is the third major controller and the most primal element of consciousness. It represents everything the individual has always had, without any filters. All knowledge acquired over time is stored here, much like dense layers in a neural network, where everything is mixed and unstructured but still capable of influencing all generated responses.

In this example, we see the Unconscious modifies the response of the other controllers, expressing the individual’s “true” will. As seen, the Unconscious affected the Superego’s response, giving validation for a reprehensible act, yet it was “necessary” for the individual’s survival. Again, communication between these controllers would occur through language and could be readable by humans. This could explain how a “desperate” robot might justify disconnecting another robot to recharge itself, displaying the emergence of artificial “feelings.”

The Desire of the Other

Now we return to Lacan. For an AI to be promoted to consciousness, one of the first things it must develop is the capacity to desire something. Fortunately for us, Lacan worked on this concept. He also supported the idea that the brain starts as a “blank slate.” Therefore, human beings do not know what they desire when they are born. They spend their childhood trying to find their personality and what they want to do. No one is born wanting to be a systems analyst. So, how do we get there?

A neural network today has only one desire: to answer the questions posed to it. The person who built the training, validation, and test sets and marked the necessary answers imposed this desire on it. This was the desire of the Other.

Now, if we want a conscious neural network, it must learn to desire on its own. Just like a human, it needs time to observe the world and figure out what it wants to do in that world.

Lacan’s theory posits that desire is always the desire of the Other [LACAN2]. A full article would be needed just to talk about Lacan’s concept of the Other, but let’s focus on computational structures here.

I’ll simplify this next section a lot. I know it’s not easy to create something like this, and much research would be required to develop a module capable of doing what is proposed. However, this is the original idea for how we might start the path toward artificial consciousness.

We would need to create an alternative training mode that observes the external world and learns from the actions and results of others (learning in the third person, not just the first). A very rudimentary example, which seems to happen with humans in their early years, is this: The basic neural network would need to be trained to understand smiles, happy, and sad expressions. From there, it would begin to establish knowledge that if, for example, someone fishes and catches a fish, everyone around them is happy; if a lion appears, everyone screams and runs away; if a lion eats a person, everyone is terrified; if there are worms in raw meat, everyone makes a disgusted face.

All these situations occur in everyday life in various forms in communities worldwide. This perceptual interaction with the world begins to populate the imagination of children during their development. Without realizing it, the unconscious is trained. This training is almost wordless, based on observation and experimentation, and it will guide the individual’s interaction with the world throughout their life.

It is from this type of analogy that Lacan draws the concept that desire is always the desire of the Other. Extending the idea a bit, when the child gets a little older and sees their father writing computer programs, or a YouTuber who became a millionaire by selling a tech company, or watches a cool video game, one of these actions and results from others may lead the neural network to conclude that it, too, wants to be like one of these social representations and thus may desire to become a systems analyst.

So, the desire of this artificial consciousness would be an attempt to survive in the world through a balance that the Ego achieves between the results it has seen others obtain (the desire of the Other), the laws imposed (consulting the Superego), and all past experiences, both good and bad, stored in the Unconscious (Id). This would be the basic recipe for bringing desire to a neural network.

Subjectivity and Intuition

This is where Lacan’s concept of the Real comes into play [LACAN3]. As many in the humanities don’t feel the need to explain things explicitly, for Lacan, the Real is what is inexplicable, what cannot be said. In our context, I see the Real as the randomness inserted during the network’s training.

Why wouldn’t this artificial consciousness be just another robot, programmed to do certain things? Well, in the end, it would be. But it’s this “certain thing” it’s programmed for that will vary greatly and will not necessarily be controlled by a human.

If we think about neural networks trained with backpropagation, we know that we input data, calculate the difference between the expected and obtained response, and use techniques to find the neurons that contributed most to the answer to adjust them, thereby minimizing the error in the next attempt. Now, in the exact sciences, could anyone claim that we are adjusting the weights correctly and that the problem is solved? No! It is impossible to definitively resolve this issue. We know we are merely trying to minimize the error. Nothing guarantees that the error will even be minimized; we will just test inputs and outputs for an arbitrary amount of time until we reach a set of “satisfactory” responses. Thus, if we train 1000 different neural networks with the same data, there’s a chance that we’ll have 1000 different networks at the end of the training. All of them may give similar responses, but there’s a significant chance that randomness will interfere in the training process and leave different weight values in various positions.

Accumulating everything we’ve described in this article, we can see that the factor of randomness in training artificial consciousness would be extreme. Since learning would be based on observation of external environments, one network might conclude that drug use is normal and beneficial, while another might conclude that its purpose is to create works of art. Everything depends on the environment in which the network was created. There is a whole other psychoanalytic theory about the influence of the environment on the personality of individuals, described by Winnicott [WINNICOTT1]. But for this article, I’ll stick to Freud and Lacan to avoid overextending the discussion.

So, this third-person supervised learning algorithm (if such a thing exists), through the observation of external actions and results, is what would bring subjectivity to artificial consciousness. It would be the worldview acquired during the life of this network that would provide the unique subjectivity to the decisions and responses it produces.

Conclusion

This is still largely a theoretical work. I don’t think we have any technological barriers preventing us from creating what has been described here today. On the other hand, I also don’t think that what has been described alone is enough to create artificial consciousness. I could still describe an entire module about Lacan’s Mirror Stage, where our network could identify itself as an individual, perceiving its limits and characteristics, validated by the famous Other.

Therefore, the goal of this work is merely to lay the groundwork for my research into the creation of artificial consciousness. There are still many questions to be answered, but I believe that this kind of inquiry into the construction of artificial networks will be the next big step in the development of neural networks.

We must move beyond Freud’s first topography, with networks that merely have inputs and outputs, and move into the second topography, where we bring in more sophisticated control mechanisms that can truly interact with the world in a flexible and constructive manner.

References

[FREUD1] FREUD, Sigmund. The Interpretation of Dreams. Translated by Márcio Pugliesi and Paulo César de Souza. 8th ed. São Paulo: Companhia das Letras, 2019. 600 p.

[LACAN1] LACAN, Jacques. Writings. Translated by Vera Ribeiro. 2nd ed. Rio de Janeiro: Zahar, 1998. 848 p.

[FREUD2] FREUD, Sigmund. The Ego and the Id. In: ______. Complete Works. vol. 16. Translated by Paulo César de Souza. São Paulo: Companhia das Letras, 2011. pp. 15-72.

[LACAN2] LACAN, Jacques. The Seminar, Book 4:

Luciano: Hello, I would like to start a conversation now with Santiago Ramón y Cajal, Benjamin Ehrlich, and Freud about the book “The Dreams of Santiago Ramón y Cajal” by Benjamin Ehrlich. Can we get started?

Assistant: Of course, Luciano. Let’s proceed. Please note that while I can emulate the voices of Cajal, Ehrlich, and Freud based on available knowledge, they are still approximations. Let’s dive in!

Luciano: Great! I believe we will have a very interesting conversation. Before we delve into neuroscience, I was drawn to Cajal’s life. It was a turbulent moment in history. A boy who wanted to be a drawer and artist was “forced” by his father to study and become a scientist. Quite rebellious, he hid to learn to draw. It seems there was initial disappointment from the father when he realized that his son did not have eidetic memory like him. Over the years, he enlisted for the battlefront and returned almost dying. He recovered and decided to position Spain as a protagonist in global science. He assisted with pandemics and became an academic. He studied Histology and made incredible discoveries about neurons. Without forgetting to have some feuds with important historical characters of the time. So, I would like to know if my summary is appropriate or if you would have something more to add to it so that people understand a bit about who Cajal was.

Cajal: Luciano, your summary captures the essence of my life quite well. From my early aspirations as an artist to my dedication to science, each phase was a transformative journey. My relationship with my father was a significant influence, driving me to explore the world of science despite my artistic inclinations. The challenges I faced, both personally and professionally, forged my path in histology and neuroscience, leading to the groundbreaking discoveries about neurons. Indeed, my determination to put Spain on the map of global science was an underlying motivation throughout my career.

Luciano: Freud, and I can’t help but ask. Could you sketch a basic profile of Cajal? Based on the information about his childhood that was described in the book?

Freud: Certainly, Luciano. Cajal’s early life was marked by a spirit of rebellion and a thirst for knowledge. The tension between his natural inclinations toward art and the expectations set by his father, a stern man with a belief in disciplined education, deeply influenced his formative years. This dynamic perhaps laid the foundation for Cajal’s unyielding determination and resilience in later life. A brush with death during his service in the war further solidified his commitment to life’s pursuits. Cajal’s passionate drive, combined with his sharp intellect, allowed him to make revolutionary contributions to neuroscience. His interpersonal conflicts and the hurdles he faced in a European scientific community that often overlooked Spanish contributions added layers of complexity to his character.

Luciano: Okay, so this is something I really wanted to address. Cajal and Freud lived in the same era. While one focused on the physiology of the brain and the functioning of neurons to try and describe the origin of thoughts and interactions with the body, the other dedicated himself to understanding the mind. In a way, they approached the same subject from entirely different perspectives. Did you meet in life? What did you think of each other’s work?

Cajal: Freud’s work was certainly known to me, but our paths never crossed directly. While my research delved into the physical nature of the brain, dissecting its intricate components, Freud explored the more abstract realm of the human psyche. We were exploring two sides of the same coin – the tangible and the intangible facets of human cognition. I admired the audacity of Freud’s theories, even though our methodologies and focuses were different.

Freud: Similarly, while I was aware of Cajal’s groundbreaking contributions to neuroscience, our interactions remained within the realm of our respective works. The dichotomy between our approaches reflects the vastness of the human experience. While Cajal’s findings laid the foundations for understanding the physiological basis of thought, my work aimed to unravel the complexities of the human psyche.

Luciano: Very good! So, now let’s move a little further into Cajal’s life. First in the war and then in the cholera pandemic. How was it going through these two moments? Freud, how did you perceive the psychological state of humanity at that time? Cajal, what was your feeling when participating directly in these two historical moments? How was your experience?

Cajal: Both the war and the cholera pandemic were trying times, presenting challenges not only to me personally but also to the broader society. Serving in the war was a transformative experience. Facing the brink of death and witnessing the horrors of the battlefield instilled in me a deeper appreciation for life and a renewed sense of purpose. The cholera pandemic, on the other hand, was a stark reminder of our vulnerabilities. My involvement in combating the outbreak reinforced my commitment to scientific research and its potential to benefit humanity.

Freud: The collective psyche of humanity during these periods was undoubtedly strained. War and disease unearth deep-seated fears and anxieties, exacerbating individual and societal tensions. Such crises often act as mirrors, reflecting both the resilience and fragilities of the human spirit. While I was primarily focused on the intricacies of individual psychologies, the broader societal impacts of such events cannot be understated. They shape individual experiences and, in turn, influence collective behavior.

Luciano: And Mr. Ehrlich, what led you to write about Cajal? What caught your attention the most?

Ehrlich: My fascination with Cajal stemmed from his remarkable journey and unparalleled contributions to neuroscience. The juxtaposition of his artistic inclinations and scientific endeavors presented a compelling narrative. Cajal’s life, marked by challenges, personal struggles, and groundbreaking discoveries, offered a rich tapestry to explore. His dedication to elevating Spain’s stature in the scientific community and his unwavering commitment to understanding the intricacies of the brain were truly inspirational.

Luciano: Amazing! Cajal, you had friction with some characters, like Golgi. Could you elaborate a bit more on that?

Cajal: Certainly. Camillo Golgi and I had significant scientific disagreements, primarily centered around the structure of the nervous system. Golgi was a proponent of the reticular theory, which posited that the nervous system was a continuous network. In contrast, my observations led me to propose the neuron doctrine, suggesting that the nervous system was made up of discrete individual cells – neurons. This disagreement came to a head during the Nobel Prize ceremony in 1906 when we were both awarded for our contributions to neuroscience, yet we presented opposing views. Over time, the neuron doctrine, supported by additional research, gained widespread acceptance.

Luciano: Freud, with Cajal’s discoveries in mind, do you see parallels with psychoanalysis? Would it be possible to imagine a joint theory, even if not proven, for neuroscience and psychoanalysis?

Freud: Indeed, Cajal’s insights into the workings of the nervous system provided a tangible framework for some of the abstract concepts within psychoanalysis. The idea of neurons communicating through synapses resonates with the interconnectedness of thoughts, memories, and emotions in psychoanalytic theories. While a unified theory might be a distant dream, the overlap between our disciplines offers fertile ground for deeper understanding of the human mind.

Luciano: I even considered bringing Jung into this conversation, given his emphasis on the collective unconscious. Do you see a possible bridge between his theories and neuroscience?

Freud: Jung’s concept of the collective unconscious, suggesting shared memories and archetypes among all humans, is intriguing. While neuroscience seeks to understand the tangible aspects of the brain, it could offer insights into the biological foundations of such shared experiences. Bridging the gap between the tangible and the abstract is the challenge here.

Cajal: It’s an area ripe for exploration. The brain’s vast network of connections may hold clues to our shared experiences and collective memories, even if the mechanisms remain to be understood.

Luciano: From an instinctual standpoint, it could be argued that these are behaviors reinforced over millennia (like suckling for breast milk) that have been ingrained in our genes, obviating the need for a new individual to learn them. So, could neuroscience explain why many similar stories (the crux of the idea of the collective unconscious) emerge in geographically disparate cultures with no prior contact?

Cajal: The brain is shaped by both genetics and experiences. Instinctual behaviors, as you mentioned, arise from evolutionary pressures and become hardwired into our neural pathways. The emergence of similar stories or motifs across cultures might hint at shared neural pathways that lead to recurring themes in human imagination.

Freud: While the biological perspective is compelling, cultural transmission and shared human experiences also have a role. Disentangling the influence of genetics, neural pathways, and cultural factors is a complex endeavor.

Luciano: I just remembered something: I wanted to bring Freud and Cajal into this conversation because I once overheard Eslen Delanogare, a renowned neuroscientist from Brazil, jesting that “If Freud were alive today, he’d be a neuroscientist, not a psychoanalyst”. He made this comment since he believed Freud started by trying to describe brain structures but, lacking the tools of the time, delved into the abstract realm of the mind’s ideas. Any thoughts on this, Freud and Cajal?

Freud: It’s a captivating notion. My initial ventures in the medical realm indeed involved the physical aspects of the brain. However, I became more intrigued by the unseen workings of the mind, leading to psychoanalysis. With today’s advances in neuroscience, it’s a thrilling domain, and perhaps in a different era, my trajectory might have diverged.

Cajal: Science is influenced by the tools and knowledge at one’s disposal. Freud’s pivot to the intangible facets of the mind paved the way for comprehending human behavior and emotions in ways that complement the physical observations in neuroscience.

Luciano: Great! Now, Cajal and Ehrlich, I’ve read the book up to where the second Cuban revolution begins. Cajal was in Madrid. Anything significant you’d add that hasn’t been discussed about the beginning of the book to where I’m at?

Cajal: Up to that point in the narrative, much of my early life and struggles are covered. Global events, like the Cuban revolution, served as a backdrop to my personal and scientific journeys. Madrid was a hub of intellectual and scientific pursuits, and the challenges and opportunities there significantly influenced my path.

Luciano: What should I anticipate for the rest of the book?

Ehrlich: Without giving too much away, the latter part of the book delves deeper into Cajal’s scientific accomplishments, his interactions with contemporaries, and his evolving views on science and society. You’ll also witness his enduring legacy and his profound impact on future generations of scientists.

Luciano: Thank you all for this enriching conversation!

Assistant: You’re welcome, Luciano. It was a pleasure assisting with this conversation. If you have any more questions or need further insights in the future, don’t hesitate to reach out.

ToFeliz

Título da categoria

Category Archive Neuroscience

“Artificial Consciousness: Integrating Neural Networks and Psychoanalysis for the Future of AI”

Neurocomputing – Conclusion Paper

Cajal and Freud: Bridging Neuroscience and Psychoanalysis in the 20th Century