# How a Camera-Based System Monitors Artificial Neural Network Creativity > A system that uses a camera to watch a screen displaying neural network activity, identifying new patterns and using a critic to decide if those patterns are worth keeping. - **Patent:** US 10423875 - **Original title:** Electro-optical device and method for identifying and inducing topological states formed among interconnecting neural modules - **Owner:** Individual - **Granted:** 2019 - **Status:** Active - **Times cited:** 1 - **Field:** ai_ml, consumer_electronics ## What it does The system monitors an artificial neural network by displaying its internal states—such as reconstruction errors or neuron activations—as color-coded values on an optical display. A camera captures this display, and a processor called a 'thalamobot' analyzes the video feed to identify new, novel topologies (patterns) in the neural chains. If the thalamobot finds a new pattern, it sends it to a 'critic' component that evaluates the merit of that pattern. Based on this evaluation, the system injects noise into an 'imagitron' to either strengthen or weaken the neural connections, effectively guiding the network's learning or idea-generation process. ## What it does NOT cover - Does not cover systems that analyze neural network data directly from memory or digital buses without an optical display and camera interface. - Does not cover general-purpose neural network training methods that lack the specific thalamobot-critic-imagitron feedback loop architecture. - Does not cover systems that do not use color-coded visual representations of neural reconstruction errors or activation histories. ## The clever bit The system treats the neural network as an external environment to be observed via a camera, using a visual feedback loop to bypass traditional software bottlenecks and introduce a 'critic' to curate machine-generated ideas. ## Real-world examples 1. Experimental neural network monitoring interfaces 2. Conceptual AI systems simulating biological thalamic filtering ## Why it matters This patent represents a conceptual approach to artificial intelligence that mimics biological processes, specifically the role of the thalamus in filtering information. By using an external optical loop to monitor internal neural states, it attempts to solve processing bottlenecks in large-scale machine learning models. It highlights a unique, albeit unconventional, methodology for managing machine creativity and learning through externalized feedback. ## Frequently asked questions ### What does How a Camera-Based System Monitors Artificial Neural Network Creativity cover? A system that uses a camera to watch a screen displaying neural network activity, identifying new patterns and using a critic to decide if those patterns are worth keeping. ### Who owns patent US 10423875? Individual owns this patent, granted in 2019. ### When does this patent expire? This patent is expected to expire on January 2, 2035, when the invention enters the public domain. ### What is patent US 10423875 cited by? This patent has been cited by 1 later patents that build on its ideas. ### What problem does this patent solve? This patent represents a conceptual approach to artificial intelligence that mimics biological processes, specifically the role of the thalamus in filtering information. By using an external optical loop to monitor internal neural states, it attempts to solve processing bottlenecks in large-scale machine learning models. It highlights a unique, albeit unconventional, methodology for managing machine creativity and learning through externalized feedback. ### What does this patent NOT cover? Does not cover systems that analyze neural network data directly from memory or digital buses without an optical display and camera interface. **Full plain-English explainer:** https://patentbrief.org/patent/us/10423875/electro-optical-device-and-method-for-identifying-and-inducing-topological-states-formed-among-interconnecting-neural-modules **Original patent:** https://patents.google.com/patent/US10423875 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How Artificial Neurons Learn from Spikes and Internal States](https://patentbrief.org/patent/us/9256215/apparatus-and-methods-for-generalized-state-dependent-learning-in-spiking-neuron) — This patent describes a method for artificial neurons to learn by adjusting their connections based on a history of incoming electrical 'spikes' and the neuron's own internal state, aiming to improve its performance. - [Efficiently Updating Connections in AI Brains](https://patentbrief.org/patent/us/9256823/apparatus-and-methods-for-efficient-updates-in-spiking-neuron-network) — This patent describes a method for updating the connections in artificial "spiking neuron networks" more efficiently by only making changes when needed, saving computational power. - [How to Update AI on Small Devices with Slow Internet](https://patentbrief.org/patent/us/20250363357/systems-and-methods-for-deploying-and-updating-neural-networks-at-the-edge-of-a-) — This patent describes a method for efficiently updating artificial intelligence models on small, internet-connected devices, like smart cameras, by sending only the changes, or 'patches,' instead of the entire updated model, which saves bandwidth. - [How Nanoparticles Form Adaptive Neural Network Connections](https://patentbrief.org/patent/us/8156057/adaptive-neural-network-utilizing-nanotechnology-based-components) — This patent describes how to build and strengthen a physical neural network using tiny nanoparticles suspended in a liquid, where electric fields make the connections learn and adapt. - [How to Automatically Expand Neural Networks by Adding New Nodes](https://patentbrief.org/patent/us/10832138/gpt-language-model-pre-training) — A method for growing artificial intelligence models by identifying underperforming parts of a network and adding new nodes based on the behavior of existing ones.