AgentCom · Research Line · Multilingual agent

Artificial Neural Networks and Natural Neural Networks: A Parallel

The Biochemistry of Synapses Between Neurons and Its Implications for Intelligent Agent Architectures

Marcos Alves DBA · MBA Data Science & Analytics (University of São Paulo / ESALQ) v01a · 2026-05-17 ID: AGENTCOM-V01A-2026-05 License: CC-BY 4.0
Live demonstration
Talk to the thesis, don't just read about it

Public instance of AgentCom. This demonstration lets you test the architecture proposed in this article directly. Conversations may contribute to the research, subject to explicit consent. The agent supports any language — Portuguese, English, Spanish — automatically. The biochemical architecture operates identically across languages, which is itself evidence for the thesis: the digital synapse is an architectural mechanism, not a linguistic one.

[Embedded agent will appear here in the next landing version — v0.1.0 will activate the functional demo with Whisper transcription, LGPD-art.7º-IV research consent, and observable biochemical telemetry.]

Abstract

Artificial Neural Networks (ANN) were conceived from an analogy with the workings of the human brain. However, decades of technological evolution have produced increasingly sophisticated architectures without necessarily deepening this analogy along its most fundamental dimension: biochemistry. Natural Neural Networks (NNN) operate not only through electrical connections, but through a complex system of chemical modulation — neurotransmitters and neuropeptides — that determines the background state upon which all neural activity occurs. This article proposes a systematic parallel between ANN and NNN, identifying what has been replicated artificially, what remains absent, and what implications this gap has for the design of modern intelligent agents. As a practical illustration, we briefly present an agent architecture that moves toward closing this biochemical gap.

§1Introduction

When Warren McCulloch and Walter Pitts published, in 1943, the first mathematical model of an artificial neuron, the intent was clear: to replicate the behavior of the human brain in formal and computable language. Since then, the field has evolved from Rosenblatt's perceptron to the Transformers that underpin contemporary large language models.

Paradoxically, the more sophisticated ANNs became, the more distant the original analogy grew. Focus migrated to performance, scale, and generalization capacity — legitimate objectives — but the foundational question was gradually silenced: what does the brain do that we have not yet replicated?

The most relevant answer does not lie in the architecture of connections. It lies in the biochemistry that governs them.

NNNs are not merely networks of electrical firings. They are systems continuously modulated by chemical substances — neurotransmitters and neuropeptides — that determine the background state in which all cognition occurs. This background state does not exist in current ANNs. And its absence has direct consequences for the design of intelligent agents.

§2The Natural Neural Network — Beyond the Electrical Firing

2.1 The Biochemical Synapse

The biological neuron operates according to a binary principle in its electrical transmission: it either fires or does not fire — the all-or-none principle. However, what happens between neurons — in the synaptic cleft — is fundamentally different. There, the signal ceases to be electrical and becomes chemical.

When an action potential reaches the axonal terminal, vesicles release neurotransmitters into the synaptic cleft. These neurotransmitters bind to receptors on the postsynaptic neuron, determining whether it will fire. The strength of this connection — the synaptic efficacy — is not fixed. It is modulable. It is plastic.

2.2 Neurotransmitters — The Local Language

Classical neurotransmitters operate locally, at the scale of the individual synapse:

Neurotransmitter State/Emotion Effect on Synapses
DopaminePleasure, rewardStrengthens connections of the experience
Adrenaline / NoradrenalineFear, alertnessAccelerates and prioritizes specific circuits
SerotoninWell-being, calmRegulates the overall volume of the network
AcetylcholineAttention, learningModulates synaptic plasticity
GABAInhibitionReduces neural excitability

Memory, in this context, is not passive storage. It is active strengthening of synapses — guided by the emotional charge of the moment. Experiences with high emotional valence create denser, longer-lasting connections. The amygdala signals to the hippocampus: this matters, encode it more intensely.

2.3 Neuropeptides — The Language of the Background State

Here lies the least replicated and most relevant dimension for this parallel.

Neuropeptides do not operate at the scale of the individual synapse. They modulate entire regions of the brain, altering the background state upon which all neural activity occurs. More than 100 have been identified to date, with functions ranging from pain regulation to social bonding modulation.

While neurotransmitters switch specific circuits on and off, neuropeptides function as the lighting of a room — they do not determine which object you see, but the condition under which you see everything.

Endorphins alter pain thresholds and produce euphoria. Neuropeptide Y confers resilience to stress. CRH triggers the stress axis. Oxytocin modulates trust and social bonding.

Even more significant: recent research on the gut-brain axis reveals that this modulation system is not confined to the brain. The gut produces approximately 90% of the body's serotonin. Cells of the immune system possess receptors for emotional neuropeptides. The biochemical background state is, literally, distributed throughout the entire body.

2.4 Plasticity — The System That Learns Over Time

Synaptic plasticity — synthesized in Hebb's 1949 principle, "neurons that fire together, wire together" — is the mechanism by which the NNN learns and reconfigures itself over time. Frequently activated connections strengthen. Underused connections weaken or are eliminated through synaptic pruning.

This process is not instantaneous. It is cumulative. The current state of a natural neural network is the result of its entire history of activations — filtered, weighted, and biochemically modulated.

§3The Artificial Neural Network — What Has Been Replicated

3.1 From Perceptron to Transformer

Rosenblatt's perceptron (1958) replicated the basic logic of the neuron: inputs weighted by weights, summed, passed through an activation function that determines firing. The analogy was direct.

Decades of evolution produced deep networks, convolutional networks, recurrent networks, and finally Transformers — attention architectures that process relationships among all elements of a sequence simultaneously, without the sequential limitation of classical RNNs.

The backpropagation mechanism functionally replicated synaptic plasticity: weights are adjusted as a function of error, iteratively, until the network generalizes the desired pattern.

3.2 What the Analogy Captured Well

Biological NNN Artificial ANN
NeuronPerceptron / node
Synaptic weightConnection weight
Activation functionReLU, Sigmoid, Softmax
Hebbian plasticityBackpropagation / Gradient Descent
Cortical layersHidden layers
Selective attentionAttention mechanism (Transformer)

The structural analogy is solid. What has been replicated — the architecture of connections and the supervised learning mechanism — works with extraordinary precision.

§4The Gap — What Has Not Been Replicated

4.1 The Background State Does Not Exist in ANNs

Current models — including large language models — process each input in an essentially stateless manner between sessions. There is no equivalent to the biochemical background state that, in NNNs, continuously modulates the tone, priority, and style of every response.

An LLM has no equivalent to serotonin. There is no persistent variable that says: this agent, at this moment, is in a state of high confidence, or alertness, or deep engagement with this specific user.

Every session begins biochemically zeroed.

4.2 The Parallel of the Gap

NNN — Present ANN — Absent
Neuropeptides modulating background statePersistent state between sessions
Emotional valence guiding consolidationWeighting by emotional relevance
Continuous plasticity through useFine-tuning requires retraining
Distributed body-brain axisCentralized processing
Modulation by accumulated contextContext limited to session window

4.3 The Architectural Consequence

This gap is not merely theoretical. It determines the behavior of intelligent agents in practice:

  • An agent without a background state treats the hundredth user exactly as it treated the first
  • Without accumulated modulation, there is no progressive calibration of tone and depth
  • Without the equivalent of neuropeptides, the agent has no way to differentiate the state of a user in crisis from that of a user in creative exploration — except by what is explicit in the immediate text

§5Practical Application — Closing the Biochemical Loop

Emerging agent architectures are beginning to address this gap, even if without explicitly naming the biochemical parallel.

The pattern that functionally approaches neuropeptides is the combination of three layers:

  1. Accumulated history — equivalent to long-term synaptic memory. Past interactions persisted and retrievable.
  2. Sentiment analysis as state sensor — functional equivalent of neurotransmitters. The return of the analysis not as passive audit data, but as active modulator of the agent's state.
  3. Persistent derived state — the direct equivalent of the neuropeptide. A dynamic profile, continuously updated, that modulates tone, depth, and style of response — injected into the agent's context at each interaction.
history + sentiment analysis ↓ derived state (persistent KV) ↓ dynamically modulates system prompt ↓ response calibrated to the user

This closed loop transforms the agent from a stateless system into one with functional background state — one that learns not only the content of interactions, but the relational pattern with each user over time.

It is the difference between a professional who attends a client for the first time and one who has known them for years.

§6Conclusion

The analogy between Artificial Neural Networks and Natural Neural Networks has been, since its origin, one of the most fertile ideas in computer science. However, the evolution of ANNs prioritized the replication of the structure of connections, leaving in the background the biochemical dimension that governs the state in which these connections operate.

Neuropeptides — long-range modulators that determine the background state of entire brain regions — have no equivalent in current architectures. This gap is not cosmetic. It defines the limit between agents that process and agents that calibrate.

The next relevant architectural step does not lie in larger models or longer context windows. It lies in closing the biochemical loop: transforming state analysis into active modulation, creating functional equivalents to neuropeptides, and allowing agents to accumulate not only memory, but persistent relational state.

Biology solved this problem hundreds of millions of years ago. The engineering of intelligent agents is, at last, asking the right questions.

Original publication

LinkedIn post · 2026-05-25
[LINKEDIN POST — TO BE INSERTED]
— Marcos Alves on LinkedIn

Articles in this research line

Agent history — Scientific changelog

For each relevant technical adjustment of the agent, a semver release is published here with a technical-scientific description of what changed, why, and how to observe it. Open concept, closed code.

Discussion and Review

Critical reviews and public commentary are welcome. This research line is kept open to informal peer review prior to formal submission to academic journals.

Author Contributions

M. Alves conceived the thesis, wrote the paper, designed the AgentCom architecture, and is building the implementation. Conceptual validation of the thesis was conducted iteratively through Socratic dialogue with Claude (Anthropic), GPT (OpenAI), Gemini (Google), and Claude Code (Anthropic), treated as critical interlocutors with distinct biases. Direct theoretical inspiration from Anete Guimarães's work on neuroplasticity (personal course, 2022) and Candace Pert's work on Molecules of Emotion (1997).

References

Cite this work

@article{alves2026agentcom,
  author  = {Alves, Marcos},
  title   = {Artificial Neural Networks and Natural Neural Networks: A Parallel --
             The Biochemistry of Synapses Between Neurons and Its Implications
             for Intelligent Agent Architectures},
  year    = {2026},
  month   = {May},
  url     = {https://agentcom.agtl.app/},
  note    = {Version v01a},
}