Method for Analyzing Neural Network Parameters for Technical Improvement and Memory Optimization
Summary
The European Patent Office granted patent EP3660748A1 to STMicroelectronics (Rousset) SAS on April 1, 2026, covering methods for analyzing neural network parameters to achieve technical improvements, specifically memory optimization through pruning and quantization techniques. The patent addresses the computational and memory efficiency challenges of deploying neural networks in resource-constrained environments such as IoT devices and edge computing systems.
What changed
The EPO published patent EP3660748A1, granting STMicroelectronics exclusive rights to methods for analyzing neural network parameters to achieve technical improvements, particularly memory gains. The patent covers techniques for optimizing neural network memory usage through parameter analysis, pruning, and quantization, enabling more efficient deployment on hardware-constrained devices.
For semiconductor manufacturers, AI chip developers, and companies deploying neural networks on edge or IoT devices, this patent establishes intellectual property barriers in the EU market for memory optimization techniques. Parties developing similar technologies in designated states (AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IT, LI, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR) should assess infringement risks and consider licensing or design-around strategies.
What to do next
- Monitor for infringement risks if developing competing neural network memory optimization technologies in EU-designated states
- Review patent claims for potential licensing opportunities related to neural network memory optimization
Archived snapshot
Apr 9, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
METHOD FOR ANALYZING A SET OF PARAMETERS OF A NEURAL NETWORK IN ORDER TO OBTAIN A TECHNICAL IMPROVEMENT, FOR EXAMPLE A MEMORY GAIN
Publication EP3660748A1 Kind: A1 Apr 01, 2026
Applicants
STMicroelectronics (Rousset) SAS
Inventors
DEMAJ, Pierre, FOLLIOT, Laurent
IPC Classifications
G06N 3/063 20060101AFI20260226BHEP G06N 3/084 20230101ALI20260226BHEP G06N 3/045 20230101ALI20260226BHEP G06N 3/0464 20230101ALI20260226BHEP G06N 3/0495 20230101ALI20260226BHEP G06N 3/09 20230101ALI20260226BHEP
Designated States
AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LI, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR
Related changes
Get daily alerts for ChangeBridge: EPO Bulletin - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from EPO.
The plain-English summary, classification, and "what to do next" steps are AI-generated from the original text. Cite the source document, not the AI analysis.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when ChangeBridge: EPO Bulletin - AI & Computing (G06N) publishes new changes.