{
  "patent_number": "US 4660166",
  "country": "US",
  "title": "How Hopfield Networks Use Resistors to Mimic Brain-Like Memory",
  "original_title": "Electronic network for collective decision based on large number of connections between signals",
  "summary": "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.",
  "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."
  ],
  "filed": "1985-01-22",
  "granted": "1987-04-21",
  "expires": "2005-01-22",
  "status": "expired",
  "holder": "California Institute of Technology",
  "holder_url": "https://patentbrief.org/company/california-institute-of-technology",
  "inventors": [
    {
      "name": "John J. Hopfield",
      "url": "https://patentbrief.org/inventor/john-j-hopfield"
    }
  ],
  "times_cited": 167,
  "tags": [
    "ai_ml",
    "semiconductors",
    "consumer_electronics"
  ],
  "abstract": "Amplifiers, optionally having complementary (positive and negative) outputs, are connected to a matrix of input and output conductors (where the output conductors are each a pair for the case of complementary amplifier outputs). Each connection is implemented with a resistors Rij=Rji connecting the output(s) of amplifiers j to the input of amplifiers i, and vice versa, where i and j are the ith and jth amplifiers not necessarily in sequence. The value of each resistor is selected for the nature of the decisional operation intended to satisfy the following circuit equation of motion <IMAGE> where Vj=g(uj) the output of amplifier j due to an input ui, Ci is the input capacitance of amplifier i, and Ri is the equivalent of pi and Rij according to the equation <IMAGE> and Rij=Rji. For the implementation of an associative memory, only positive (or negative) output terminals need be connected by resistors of unit value to input terminals of amplifiers i and j for the amplifier i in which a binary 1 is to be stored. (The amplifier j is one or more of the other amplifiers.) The outputs of the array of amplifiers will produce the entire word stored in response to a few bit-1 input signals Ii to amplifiers so connected by resistors Rij. For problem solution, the resistance Rij=Rji is selected to have a value that, with appropriate signals at all input conductors (perhaps zero) the network will collectively drive to a stable state at the complementary output terminals which provide an output code word that is a very good solution to the problem.",
  "url": "https://patentbrief.org/patent/us/4660166/electronic-network-for-collective-decision-based-on-large-number-of-connections-between-signals",
  "markdown_url": "https://patentbrief.org/patent/us/4660166/electronic-network-for-collective-decision-based-on-large-number-of-connections-between-signals/md",
  "google_patents_url": "https://patents.google.com/patent/US4660166",
  "relatedPatents": [
    {
      "patentNumber": "10248907",
      "countryCode": "US",
      "title": "How a Single Electronic Component Can Learn and Process AI Data",
      "url": "https://patentbrief.org/patent/us/10248907/resistive-processing-unit"
    },
    {
      "patentNumber": "11741188",
      "countryCode": "US",
      "title": "How a Chip Uses Memory to Speed Up AI Calculations",
      "url": "https://patentbrief.org/patent/us/11741188/hardware-accelerated-discretized-neural-network"
    },
    {
      "patentNumber": "10956815",
      "countryCode": "US",
      "title": "How to Fix Faulty Memory Cells in AI Chips",
      "url": "https://patentbrief.org/patent/us/10956815/killing-asymmetric-resistive-processing-units-for-neural-network-training"
    },
    {
      "patentNumber": "10410117",
      "countryCode": "US",
      "title": "How to Save and Reuse Skills Learned by Artificial Intelligence Hardware",
      "url": "https://patentbrief.org/patent/us/10410117/method-and-a-system-for-creating-dynamic-neural-function-libraries"
    },
    {
      "patentNumber": "10423875",
      "countryCode": "US",
      "title": "How a Camera-Based System Monitors Artificial Neural Network Creativity",
      "url": "https://patentbrief.org/patent/us/10423875/electro-optical-device-and-method-for-identifying-and-inducing-topological-states-formed-among-interconnecting-neural-modules"
    }
  ]
}