Product Design, Manufacturing & Innovation Resources

ニューラルネットワークに関する最新の出版物と特許

Neural Networks

ヒント:以下の選択肢に加えて、2つのデータベース全体を検索およびフィルタリングできます。

> 無料の出版物検索ツール < 著者、トピック、キーワード、日付、または雑誌名で検索できます。

> 無料特許検索ツール < 欧州特許庁の英語による特許情報。

これは、ニューラルネットワークに関する世界中の英語の出版物と特許の最新セレクションです。多数のオンライン科学ジャーナルから、ニューラルネットワーク、人工ニューロン、エポック、ニューラルアーキテクチャ、機械学習、深層学習、サポートベクターマシンといったキーワードで分類・絞り込んでいます。

Uncertainty-aware prediction of the glass transition temperature of aliphatic polycarbonates using ensemble machine learning

Published on 2026-06-16 by Yoshifumi Amamoto, Ryunosuke Ito, Mikako Murakami, Kohzo Ito, Kazuki Fukushima @NATURE

Abstract: Polymer Journal, Published online: 16 June 2026; doi:10.1038/s41428-026-01208-yAliphatic polycarbonates (APCs) are promising sustainable polymers, but improving their physical properties remains a challenge. Here, uncertainty-aware machine learning was applied to predict the glass transition temperature (Tg) of APCs using ensembles of molecular descriptors and algorithms. Tg data from over 50 APCs were analyzed, and the top five models provided moderate predictive accuracy with quantified uncert[...]


Our summary: This study applies uncertainty-aware machine learning to predict the glass transition temperature of aliphatic polycarbonates. An ensemble of molecular descriptors and algorithms was used to analyze Tg data from over 50 APCs. The framework enhances the reliability of polymer property predictions and aids in designing high-performance sustainable polymers.

machine learning, glass transition temperature, aliphatic polycarbonates, predictive modeling

Publication

Mapping individual differences in neurophysiological signals

Published on 2026-06-15 by @MIT

Abstract: AbstractNormative modeling has become a cornerstone of computational neuroscience, offering a powerful framework for detecting individual deviations from typical brain function. This review traces its trajectory in electrophysiology of the brain, from early studies in the 1970s, through a period of relative neglect, to its recent revival driven by machine learning advances and the availability of large-scale datasets. We provide a structured overview of this evolution, showing the shift from sma[...]


Our summary: This review discusses the evolution of normative modeling in neurophysiology, highlighting its resurgence due to machine learning and large datasets. It compares key studies and identifies challenges such as standardization and comparability. The authors advocate for unified efforts and novel features to enhance individualized brain mapping for clinical applications.

neurophysiology, normative modeling, machine learning, individualized mapping

Publication

New energy power electronic DC motor control system based on a fuzzy neural network

Published on 2026-06-13 by @OXFORD

Abstract: AbstractBased on the uncertainty and control effect of electronic DC motors, a neural network algorithm, fuzzy control, and fuzzy neural network are designed. First, a small signal model controlled by a virtual direct filter motor is developed, and the stability and dynamic characteristics of the control strategy are analyzed. Next, the influence of the distribution map of the system based on the closed-loop transmission function, inertia coefficient, and step response curve is explored. Finally[...]


Our summary: A new control system for electronic DC motors is developed using fuzzy neural networks. The system s stability and dynamic characteristics are analyzed through a small signal model. Computer simulations validate the effectiveness of the proposed control strategy.

fuzzy neural network, DC motor control, stability analysis, computer simulation

Publication

Machine learning-based reconstruction of 2D MRI for quantitative morphometry in epilepsy

Published on 2026-06-11 by @MIT

Abstract: In the original article, we report a clinical cohort comprised of healthy controls (HC), and two phenotypic subgroups of people with idiopathic generalised epilepsy: 42 people with drug-resistant idiopathic generalised epilepsy, and 33 (31 following exclusions) people with drug-sensitive idiopathic generalised epilepsy—pwDRIGE and pwDSIGE in the original manuscript, respectively. Following a review of archived data, it was flagged that these phenotypic labels had been mistakenly assigned at an[...]


Our summary: This study involves a clinical cohort of healthy controls and two subgroups of people with idiopathic generalized epilepsy. The initial phenotypic labels were corrected, revealing one subgroup with drug-resistant focal epilepsy and another with generalized epilepsy. Updated demographic information and subgroup comparisons are provided in revised tables and figures.

machine learning, MRI reconstruction, epilepsy, morphometry

Publication

Systems and methods for using client system intelligence for distributed service system configuration

Patent published on the 2026-06-11 in US under Ref US20260163813 by STRIPE INC [US] (Gehman Samuel Ishmael [us], Jermsurawong Jermsak [us], Vafeias Efstathios [us], Brown Jonathon Daniel [us], Kedia Gautam [us])

Abstract: A method and apparatus for executing a service of a server computer system for a client system are described. The method may include defining a client system descriptor file that includes a set of signals suitable for input into a large language machine learning model (LLM), and collecting data associated with a first client system that is representative of the set of signals. The data can then be compressed into the set of signals for a first client system descriptor file allocated for the clie[...]


Our summary: The method involves defining a client system descriptor file with signals for a large language model. Data from a client system is collected and compressed into this descriptor file. A query is executed using the descriptor file, leading to actions by the server s service based on the model s output.

client system intelligence, distributed service configuration, machine learning model, client system descriptor file

Patent

System and method for edge-inserted wavelength-multiplexed diagonal-based photonic computing and control

Patent published on the 2026-06-11 in WO under Ref WO2026123016 by UNIV OF ROCHESTER [US] (Iyer Arjun [us], Renninger William [us])

Abstract: An exemplary system and method for distributed processing neural network (NN) or deep learning (DL) models by (i) optically encoding and multiplexing, at a transmitter (e.g., cloud server), a plurality of NN or DL model parameters into a single optical beam and (ii) processing, at a receiver (e.g., phone, computer, etc.), the plurality of NN or DL model parameters optically encoded within the single optical beam. By optically encoding a cyclically shifted offset diagonal of a weight matrix at a [...]


Our summary: The system encodes and multiplexes neural network parameters into a single optical beam for efficient processing. A receiver decodes these parameters using a single photodetector to perform matrix-vector multiplications. This method enhances distributed processing capabilities for deep learning applications.

wavelength-multiplexing, photonic computing, neural networks, deep learning

Patent

A method for life-cycle-management of artificial intelligence models for measurement inference in a wireless communication system

Patent published on the 2026-06-11 in WO under Ref WO2026118213 by ZTE CORP [CN] (Song Xiaohui [cn], Dong Fei [cn], Liu Jing [cn])

Abstract: This disclosure is directed generally to wireless communication networks and particularly to managing inference and training of Artificial Intelligence (AI) or Machine Learning (ML) models used for measurement prediction and measurement event prediction in mobility provisioning. The disclosed implementations provide a scheme for exchange of AI/ML capability and configuration information between wireless terminals and a wireless network to effectively select and configure AI/ML models or algorith[...]


Our summary: This method manages the life cycle of AI models for measurement inference in wireless networks. It facilitates the exchange of AI/ML configurations between terminals and networks. The approach aims to enhance predictive mobility management for wireless devices.

AI model management, wireless communication, measurement inference, predictive mobility management

Patent

System and method for autonomous gearshift deduplication in an storage system

Patent published on the 2026-06-11 in US under Ref US20260161315 by DELL PRODUCTS L P [US] (Vankamamidi Vamsi [us], Kachmar Maher [us])

Abstract: [0000] A method, computer program product, and computing system for tracing a variable set of deduplication metrics for one or more deduplication data sets, applying a regression-based machine learning (ML) model to the variable set of deduplication metrics, and generating a weighted deduplication score and a weighted compression score for each data sample. The method may further include selecting one or more of a compression algorithm and a deduplication parameter based on one or more of the we[...]


Our summary: The method involves tracing deduplication metrics and applying a regression-based ML model to generate scores. It selects compression algorithms and deduplication parameters based on these scores. A flushing manager performs in-line deduplication on front-end IO write data using the selected algorithms and parameters.

deduplication, machine learning, compression, storage system

Patent

取り上げるトピック: ニューラルネットワーク、人工ニューロン、エポック、ニューラルアーキテクチャ、機械学習、深層学習、サポートベクターマシン、動的手振り認識、ベンチマークデータセット、事前学習済み重み、トレーニングデータ、トレーニングデータセット、設計スナップショット、樹状ニューロンモデル、シナプス可塑性、強化動的グループ化差分進化、YOLOv8、およびByteTrack。

歴史的背景

1965
1970
1970
1974-11-15
1980
1980
1980
1964
1968
1970
1970
1975
1980
1980
1980

(日付が不明または関連性がない場合、例えば「流体力学」などでは、その注目すべき出現時期の概算値が提示されます。)

フルサイズの画像とダウンロードは、登録会員のみが100%無料で利用できます。