Training AI Models Across Different Computers

This 2026 patent describes a way to train AI models on one computer, send a version to another computer for further training with private data, and then update the original model with the improvements.

What it covers

This patent details a method for distributed AI training. A central computer (first host system) trains an initial neural network using data that has already been filtered from multiple remote sources. This initial network is then sent to a remote computer (second host system). The remote computer further trains this network using its own private data, creating a customized version. This customized network is then installed and used on the remote computer to process its live data stream. Crucially, the remote computer sends updated coefficients back to the central computer, allowing the original network to be improved based on the private data insights gained remotely. For example, a central server could train a general security camera AI, send it to individual homes, where each home's camera further trains it on local activity, and then sends back anonymized updates to improve the central AI.

What it doesn't cover

• —Training that only occurs on a single computer system.
• —Using a neural network that is not further trained on private, local data at the second host system.
• —Sending raw, unfiltered event data from the remote systems to the first host system.
• —Updating the central neural network without receiving updated coefficients from a remote system.
• —Training that does not involve evaluating the neural network at both the first and second host systems.

The clever bit

The innovation lies in the two-way learning process: a central model is improved by private, local data without that data ever leaving the local system, and the central model, in turn, helps filter data for the local system. This creates a continuous, privacy-preserving feedback loop for AI model improvement.

Why it matters

This patent addresses the challenge of training powerful AI models while respecting data privacy. It enables AI systems, like those used in security or smart home devices, to learn from diverse, real-world data without needing to collect all that sensitive data in one central location. This approach is key for developing intelligent systems that can adapt to local conditions while maintaining a globally improved model.

Real-world examples

• 1.Security camera systems that learn local activity patterns.
• 2.Smart home devices that personalize their functions based on user behavior.
• 3.Industrial monitoring systems that adapt to specific machine behaviors.