Training neural networks
A method of training an artificial neural network uses a computer configured as a plurality of interconnected neural units arranged in a layered network including an input layer having a network input, and an output laye…
Original patent title: “Training neural networks”
What this patent covers
The actual claim
A method of training an artificial neural network uses a computer configured as a plurality of interconnected neural units arranged in a layered network including an input layer having a network input, and an output layer having a network output. A neural unit has a first subunit and a second subunit. The first subunit having one or more first inputs, and a corresponding first set of variables for operating upon the first inputs to provide a first output. The first set of variables can change in response to feedback representing differences between desired network outputs for selected network inputs and actual network outputs. The second subunit has a plurality of second inputs, and a corresponding second set of variables for operating upon said second inputs to provide a second output. The second set of variables can change in response to differences between desired network outputs for selected network inputs and actual network outputs. The computer provides an activating variable representing the difference between current second output and previous second outputs. A series of examples of data is provided as network input to said network. The activating variable is added to the feedback to accelerate the change of said first set of variables. The actual resulting network outputs are compared to desired outputs corresponding to the examples. The examples are iterated until the network outputs converge to a solution.
What this patent does NOT cover
The boundaries
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Patent Abstract
Patent abstract
A method of training an artificial neural network uses a computer configured as a plurality of interconnected neural units arranged in a layered network including an input layer having a network input, and an output layer having a network output. A neural unit has a first subunit and a second subunit. The first subunit having one or more first inputs, and a corresponding first set of variables for operating upon the first inputs to provide a first output. The first set of variables can change in response to feedback representing differences between desired network outputs for selected network inputs and actual network outputs. The second subunit has a plurality of second inputs, and a corresponding second set of variables for operating upon said second inputs to provide a second output. The second set of variables can change in response to differences between desired network outputs for selected network inputs and actual network outputs. The computer provides an activating variable representing the difference between current second output and previous second outputs. A series of examples of data is provided as network input to said network. The activating variable is added to the feedback to accelerate the change of said first set of variables. The actual resulting network outputs are compared to desired outputs corresponding to the examples. The examples are iterated until the network outputs converge to a solution.
Patent Journey
From filing to expiry
Patent Filed
1988
Patent Granted
1990 · 1yr after filing
Patent Expired
2008
PatentBrief Score
Impact Score
Early stage
Citation count
29/40
Moderately cited
Claim breadth
2/20
Narrow claims
Recency
0/20
Older than 20 years
Assignee scale
0/20
Independent or smaller assignee
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
The original legal language
Original claims
3 claims as filed with the patent office.
Citations
Patent lineage
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 12564871 · 2026
A Fixture for Cleaning Showerheads with Multiple Separate Chambers
This patent describes a cleaning device for showerheads that uses a fixture with three or more separate internal compartments and channels to direct cleaning fluid to the showerhead's upper surfaces.
ASM IP HOLDING BV
US 12324579 · 2025
Surgical Stapler Battery Health Check During Operation
This patent describes a powered surgical stapler that can detect if some of its rechargeable battery cells are damaged while it's actually firing staples, helping ensure the procedure finishes safely.
CILAG GMBH INT
US 12471982 · 2025
Surgical Tool That Combines Energy Treatment and Stapling
CILAG's patent details a surgical instrument that applies therapeutic energy to tissue, monitors its properties, then deploys staples, adapting the stapling based on the initial energy treatment and monitoring.
CILAG GMBH INT
US 11918209 · 2024
Real-Time Surgical Instrument Status on Live Video During Operations
This patent describes a surgical system that shows live video from inside the body and overlays important information about the surgical tool directly onto the screen, helping surgeons operate more precisely.
CILAG GMBH INT
US 8697359 · 2014
How to Use CRISPR-Cas9 to Edit Genes in Human Cells
This patent describes a method and system for precisely altering gene expression in eukaryotic cells, including human cells, using an engineered CRISPR-Cas9 system that targets and cleaves specific DNA sequences.
Massachusetts Institute of Technology
US 4683195 · 1987
How to Make Many Copies of a Specific DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a fundamental process for making millions of copies of a specific DNA or RNA segment from a tiny sample, enabling its detection.
Cetus Corp
Patent monitoring