Rethinking Intelligence: Brain-like Neuron Network

2026-01-27

AI Summary

This work proposes a brain-inspired neural network paradigm—BNN—and introduces LuminaNet, its first instantiation: a dynamic architecture that autonomously evolves its structure without relying on convolution or self-attention mechanisms. Departing from conventional artificial neural networks that depend on handcrafted architectures and inductive biases, LuminaNet eschews fixed topologies and human-imposed priors, instead leveraging neuroscience-inspired mechanisms to enable adaptive structural reconfiguration. Experimental results demonstrate that LuminaNet achieves 11.19% and 5.46% higher accuracy than LeNet-5 and AlexNet, respectively, on CIFAR-10, outperforming various MLP and Vision Transformer (ViT) models. On the TinyStories benchmark, it attains a perplexity of 8.4 while reducing computational cost by 25% and peak memory usage by nearly 50%.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Large Vision Models
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Since their inception, artificial neural networks have relied on manually designed architectures and inductive biases to better adapt to data and tasks. With the rise of deep learning and the expansion of parameter spaces, they have begun to exhibit brain-like functional behaviors. Nevertheless, artificial neural networks remain fundamentally different from biological neural systems in structural organization, learning mechanisms, and evolutionary pathways. From the perspective of neuroscience, we rethink the formation and evolution of intelligence and proposes a new neural network paradigm, Brain-like Neural Network (BNN). We further present the first instantiation of a BNN termed LuminaNet that operates without convolutions or self-attention and is capable of autonomously modifying its architecture. We conduct extensive experiments demonstrating that LuminaNet can achieve self-evolution through dynamic architectural changes. On the CIFAR-10, LuminaNet achieves top-1 accuracy improvements of 11.19%, 5.46% over LeNet-5 and AlexNet, respectively, outperforming MLP-Mixer, ResMLP, and DeiT-Tiny among MLP/ViT architectures. On the TinyStories text generation task, LuminaNet attains a perplexity of 8.4, comparable to a single-layer GPT-2-style Transformer, while reducing computational cost by approximately 25% and peak memory usage by nearly 50%. Code and interactive structures are available at https://github.com/aaroncomo/LuminaNet.

Problem

• artificial neural networks
• biological neural systems
• intelligence evolution
• brain-like architecture
• neural network paradigm

Innovation

• Brain-like Neural Network
• Self-evolving Architecture
• Dynamic Structure Modification
• Convolution-free
• Neuroscience-inspired AI