# How Hopfield Networks Use Resistors to Mimic Brain-Like Memory > A foundational patent describing an electronic circuit that uses a grid of resistors to perform computations, effectively creating an artificial neural network that can store and recall patterns. - **Patent:** US 4660166 - **Original title:** Electronic network for collective decision based on large number of connections between signals - **Owner:** California Institute of Technology - **Granted:** 1987 - **Status:** Public domain (expired) - **Times cited:** 167 - **Field:** ai_ml, semiconductors, consumer_electronics ## What it does This patent describes a hardware architecture where multiple amplifiers are connected in a dense matrix using resistors. Each resistor acts as a weight, determining how much the output of one amplifier influences the input of another. By setting these resistance values, the network can be programmed to store specific patterns or solve optimization problems. When the system is given a partial or noisy input, the interconnected resistors cause the circuit to settle into a stable state, effectively reconstructing the full stored pattern or finding a solution to a complex problem. ## What it does NOT cover - Does not cover software-based neural network simulations running on standard CPUs. - Does not cover digital logic gates or traditional von Neumann computing architectures. - Does not cover learning algorithms that automatically adjust resistor values during operation (this patent focuses on fixed, programmed resistances). - Does not cover non-electronic implementations, such as optical or biological neural models. ## The clever bit The innovation lies in using the physical laws of electricity—specifically Kirchhoff's circuit laws—to perform computation. Instead of calculating results step-by-step, the network 'finds' the solution by naturally evolving toward a state of lowest energy. ## Real-world examples 1. Early hardware-based associative memory systems 2. Neuromorphic computing research platforms 3. Analog neural network circuit prototypes ## Why it matters This is a seminal document in the history of artificial intelligence. John Hopfield's work provided a physical, electronic blueprint for associative memory, bridging the gap between theoretical neuroscience and practical circuit design. It proved that simple, collective interactions between basic components could produce complex, brain-like computational behavior. ## Frequently asked questions ### What does How Hopfield Networks Use Resistors to Mimic Brain-Like Memory cover? A foundational patent describing an electronic circuit that uses a grid of resistors to perform computations, effectively creating an artificial neural network that can store and recall patterns. ### Who owns patent US 4660166? California Institute of Technology owns this patent, granted in 1987. ### When does this patent expire? This patent has expired and is now in the public domain — anyone can use the invention freely. ### What is patent US 4660166 cited by? This patent has been cited by 167 later patents that build on its ideas. ### What problem does this patent solve? This is a seminal document in the history of artificial intelligence. John Hopfield's work provided a physical, electronic blueprint for associative memory, bridging the gap between theoretical neuroscience and practical circuit design. It proved that simple, collective interactions between basic components could produce complex, brain-like computational behavior. ### What does this patent NOT cover? Does not cover software-based neural network simulations running on standard CPUs. **Full plain-English explainer:** https://patentbrief.org/patent/us/4660166/electronic-network-for-collective-decision-based-on-large-number-of-connections-between-signals **Original patent:** https://patents.google.com/patent/US4660166 --- _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 a Single Electronic Component Can Learn and Process AI Data](https://patentbrief.org/patent/us/10248907/resistive-processing-unit) — This patent describes a tiny electronic component called a resistive processing unit (RPU) that acts like a brain cell in an artificial intelligence network, storing and processing information directly within its changing electrical resistance. - [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 a Chip Uses Memory to Speed Up AI Calculations](https://patentbrief.org/patent/us/11741188/hardware-accelerated-discretized-neural-network) — This patent describes a specialized computer chip that uses non-volatile memory and analog signals to quickly perform calculations for artificial intelligence, especially for neural networks that need to remember past information. - [How IBM Uses Resistive Memory Chips to Speed Up AI Training](https://patentbrief.org/patent/us/10740671/convolutional-neural-networks-using-resistive-processing-unit-array) — A method for running AI neural networks directly on specialized hardware chips that store data as electrical resistance, making them faster and more energy-efficient than standard processors. - [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.