公开(公告)号：US11884296B2

公开(公告)日：2024-01-30

申请号：US17128554

申请日：2020-12-21

申请人： QUALCOMM Incorporated

发明人： Hee Jun Park ,  Abhinav Goel

IPC分类号： B60W60/00 ,  G06N3/045 ,  G06N3/00 ,  G06N3/042 ,  G06N7/04

CPC分类号： B60W60/0015 ,  B60W60/0013 ,  G06N3/002 ,  G06N3/042 ,  G06N3/045 ,  G06N7/046

摘要： Embodiments include methods performed by a processor of a vehicle for allocating processing resources to concurrently-executing neural networks. The methods may include determining a priority of each of a plurality of neural networks executing on a vehicle processing system based on a contribution of each neural network to overall vehicle safety performance, and allocating computing resources to the plurality of neural networks based on the determined priority of each neural network. In some embodiments, the methods may dynamically adjust hyperparameters of one or more neural networks.

公开(公告)号：US20160300121A1

公开(公告)日：2016-10-13

申请号：US15188729

申请日：2016-06-21

申请人： SUPERFISH LTD.

发明人： Michael CHERTOK ,  Alexander LORBERT ,  Adi PINHAS

IPC分类号： G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06K9/46 ,  G06K7/14

CPC分类号： G06K9/627 ,  G06K7/1482 ,  G06K9/469 ,  G06N3/02 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/084 ,  G06N7/046 ,  G06T2207/20084

摘要： A method for representing an input image, the method including the steps of applying a trained neural network (NN) on the input image, selecting a plurality of feature maps, determining a location of each of the feature maps in an image space of the input image, defining a plurality of interest points of the input image, representing the input image as a graph according to the interest points and geometric relations between the interest points, and employing the graph for performing a visual task, the graph including a plurality of vertices and edges, and maintaining the data respective of the geometric relations, the feature maps being selected of an output of at least one selected layer of the trained NN according to values attributed to the feature maps by the trained NN, the interest points of the input image being defined based on the locations corresponding to the feature maps.

摘要翻译： 一种用于表示输入图像的方法，所述方法包括以下步骤：在所述输入图像上应用经过训练的神经网络（NN），选择多个特征图，确定所述输入的图像空间中的每个特征图的位置 图像，定义输入图像的多个兴趣点，根据兴趣点和兴趣点之间的几何关系将输入图像表示为图形，并且使用用于执行视觉任务的图，该图包括多个顶点 和边缘，并且保持数据相应的几何关系，特征图被选择为训练的NN的至少一个所选层的输出，根据经训练的NN归因于特征图的值，输入的兴趣点 基于与特征图对应的位置来定义图像。

公开(公告)号：US5828812A

公开(公告)日：1998-10-27

申请号：US432801

申请日：1995-05-02

申请人： Emdadur Rahman Khan ,  William Shields Neely

发明人： Emdadur Rahman Khan ,  William Shields Neely

IPC分类号： G06N3/04 ,  G06N7/04 ,  G06E1/00 ,  G06E3/00 ,  G06F15/18 ,  G06G7/00

CPC分类号： G06N7/046 ,  G06N3/0436 ,  Y10S706/90

摘要： A recurrent, neural network-based fuzzy logic system includes in a rule base layer and a membership function layer neurons which each have a recurrent architecture with an output-to-input feedback path including a time delay element and a neural weight. Further included is a recurrent, neural network-based fuzzy logic rule generator wherein a neural network receives and fuzzifies input data and provides data corresponding to fuzzy logic membership functions and recurrent fuzzy logic rules.

摘要翻译： 一种基于神经网络的模糊逻辑系统包括在规则基础层和隶属函数层神经元中，每个神经元具有具有包括时间延迟元素和神经重量的输出到输入反馈路径的复现架构。 还包括一种基于神经网络的模糊逻辑规则生成器，其中神经网络接收和模糊化输入数据并提供对应于模糊逻辑隶属函数和循环模糊逻辑规则的数据。

公开(公告)号：US5579439A

公开(公告)日：1996-11-26

申请号：US036634

申请日：1993-03-24

申请人： Emdadur R. Khan

发明人： Emdadur R. Khan

IPC分类号： G06N3/04 ,  G06N7/04 ,  G06F9/44 ,  G06F15/80

CPC分类号： G06N3/0436 ,  G06N7/046 ,  Y10S706/90

摘要： A fuzzy logic design generator for providing a fuzzy logic design for an intelligent controller in a plant control system includes an artificial neural network for generating fuzzy logic rules and membership functions data. These fuzzy logic rules and membership functions data can be stored for use in a fuzzy logic system for neural network based fuzzy antecedent processing, rule evaluation and defuzzification, thereby avoiding heuristics associated with conventional fuzzy logic algorithms. The neural network, used as a fuzzy rule generator to generate fuzzy logic rules and membership functions for the system's plant controller, is a multilayered feed-forward neural network based upon a modified version of a back-propagation neural network and learns the system behavior in accordance with input and output data and then maps the acquired knowledge into a new non-heuristic fuzzy logic system. Interlayer weights of the neural network are mapped into fuzzy logic rules and membership functions. Antecedent processing is performed according to a weighted product of the antecedents. One layer of the neural network is used for performing rule evaluation and defuzzification.

摘要翻译： 用于为工厂控制系统中的智能控制器提供模糊逻辑设计的模糊逻辑设计发生器包括用于生成模糊逻辑规则和隶属函数数据的人造神经网络。 这些模糊逻辑规则和隶属函数数据可以存储在模糊逻辑系统中，用于基于神经网络的模糊前提处理，规则评估和去模糊化，从而避免与常规模糊逻辑算法相关的启发式。 神经网络作为模糊规则生成器，用于为系统的工厂控制器生成模糊逻辑规则和隶属函数，是基于反向传播神经网络的修改版本的多层前馈神经网络，并学习系统的行为 根据输入和输出数据，然后将获取的知识映射到新的非启发式模糊逻辑系统中。 神经网络的层间权重映射到模糊逻辑规则和隶属函数中。 先行处理是根据先前的加权产物进行的。 神经网络的一层被用于执行规则评估和去模糊化。

公开(公告)号：US5416888A

公开(公告)日：1995-05-16

申请号：US113514

申请日：1993-08-30

申请人： Yoshiyuki Shimokawa

发明人： Yoshiyuki Shimokawa

IPC分类号： G06F15/18 ,  G05B13/02 ,  G06F9/44 ,  G06N3/04 ,  G06N7/04 ,  G06N99/00 ,  G05B13/00

CPC分类号： G05B13/0285 ,  G06N3/0436 ,  G06N7/046 ,  Y10S706/90

摘要： A multi-layered type neural network for a fuzzy reasoning in which an if-part of a fuzzy rule is expressed by a membership function and a then-part of the fuzzy rule is expressed by a linear expression, the network comprising an if-part neural network for receiving if-part variables of all the fuzzy rules and calculating if-part membership values of all the fuzzy rules, an intermediate neural network for calculating, as a truth value of the premise of each fuzzy rule, a product of the if-part membership values for all the if-part variables, and a then-part neural network for calculating a first sum of the truth values of the premise of all the fuzzy rules, a second sum of a product of the truth values of the premise of all the fuzzy rules and then-part outputs of all the fuzzy rules, and dividing the second sum by the first sum to obtain a quotient as an inferential result.

摘要翻译： 一种用于模糊推理的多层次神经网络，其中模糊规则的if部分由隶属函数表示，然后由模糊规则的一部分由线性表达式表示，网络包括if部分 神经网络用于接收所有模糊规则的if-part变量，并计算所有模糊规则的if-part隶属度值，计算的中间神经网络，作为每个模糊规则的前提的真值，if - 对于所有if部分变量的一部分成员关系值，以及用于计算所有模糊规则的前提的真值的第一和的部分神经网络，即前提的真值的乘积的第二和 所有模糊规则和所有模糊规则的部分输出，并将第二和除以第一和，以获得商为推论结果。

公开(公告)号：US12045224B2

公开(公告)日：2024-07-23

申请号：US16747359

申请日：2020-01-20

申请人： s â f.ai, Inc.

发明人： Ahmed Masud

IPC分类号： G06N3/08 ,  G06F16/23 ,  G06N3/045 ,  G06N3/06 ,  G06N7/02 ,  G06N7/04

CPC分类号： G06F16/2365 ,  G06N3/045 ,  G06N3/061 ,  G06N3/08 ,  G06N7/023 ,  G06N7/046

摘要： Various embodiments include methods and devices for transforming a data block into weights for a neural network. Some embodiments may include training a first neural network of a cybernetic engram to reproduce the data block, and replacing the data block in memory with weights used by the first neural network to reproduce the data block.

公开(公告)号：US20240078455A1

公开(公告)日：2024-03-07

申请号：US18307995

申请日：2023-04-27

申请人： University of South Florida

发明人： Peter Joseph Jorgensen

IPC分类号： G06N7/04 ,  G06N5/043

CPC分类号： G06N7/046 ,  G06N5/043

摘要： A Hierarchical Ensembles of Autonomous Decision Systems (HEADS) system with a recursive ensemble weighting update is proposed. The system is built on fuzzy logic leading to an understandable and tractable logic design that leverages subject matter experts to design system operations. The hierarchical structure enables multi-layered logic for granular control and decisions incorporating inferred information. The control output from each ensemble is a mixture from independently trained fuzzy systems processed through a gating network. The gating network weights are updated recursively. Each expert uses a subset of the input space to minimize per-expert complexity and support ensemble robustness under uncertain or evolving state realizations and operating environments. Finally, autonomy based on fuzzy systems offers the potential for increased human comprehension of an agent's status and decision logic.

公开(公告)号：US11709463B2

公开(公告)日：2023-07-25

申请号：US17975198

申请日：2022-10-27

申请人： Yancheng Institute Of Technology ,  YCIT Technology Transfer Center Co., Ltd.

发明人： Ye Yuan ,  Linfeng Chen ,  Cheng Ding ,  Aijie Wang ,  Tianming Chen ,  Yunjiang Yu ,  Wanxin Yin

IPC分类号： G05B13/02 ,  G06F18/2135 ,  G01N33/18 ,  G06N7/04

CPC分类号： G05B13/0285 ,  G01N33/1806 ,  G06F18/2135 ,  G06N7/046

摘要： A control method based on an adaptive neural network model for dissolved oxygen of an aeration system includes: obtaining related water quality monitoring data of a sewage treatment plant, and performing data preprocessing on the related water quality monitoring data; performing principal component analysis on the preprocessed related water quality monitoring data and a dissolved oxygen concentration of the aeration system through a principal component analysis method, and determining a water quality parameter with a highest rate of contribution to a principal component; taking the water quality parameter with the highest rate of contribution to the principal component, and predicting a dissolved oxygen concentration of the aeration system; and optimizing a dissolved oxygen predictive value obtained by means of the adaptive neural network model to obtain an optimal regulation value, and performing online regulation on a fuzzy control system of the adaptive neural network model.

公开(公告)号：US20170330076A1

公开(公告)日：2017-11-16

申请号：US15531212

申请日：2014-11-26

申请人： CURIOUS Al OY

发明人： Harri VALPOLA

IPC分类号： G06N3/08 ,  G06N99/00 ,  G06N7/04

CPC分类号： G06N3/084 ,  G06N3/02 ,  G06N7/046 ,  G06N20/00

摘要： Disclosed is a neural network structure enabling efficient training of the network and a method thereto. The structure is a ladder-type structure wherein one or more lateral input(s) is/are taken to decoding functions. By minimizing one or more cost function(s) belonging to the structure the neural network structure may be trained in an efficient way.

公开(公告)号：US20140087749A1

公开(公告)日：2014-03-27

申请号：US13969794

申请日：2013-08-19

申请人： YUAN ZE UNIVERSITY

发明人： JEICH MAR ,  KUEI-CHOU TSAI ,  YU-TING WANG

IPC分类号： H04L5/00 ,  G06N7/04

CPC分类号： H04L5/0037 ,  G06N3/0436 ,  G06N7/046 ,  H04L5/0023 ,  H04L5/0058 ,  H04W52/20 ,  H04W52/241 ,  H04W52/243 ,  H04W52/267

摘要： Intelligent technique is an effective method to perform the network resource management. A three layer cascade adaptive neural fuzzy inference system (ANFIS) based intelligent controller is proposed for the mobile wireless network to optimize the maximum average throughput, minimum transmit power and interference for multimedia call services. The proposed intelligent controller is designed with a three layer cascade architecture, which mainly contains an ANFIS rate controller (ARC) in the first layer, an ANFIS power controller (APC) in the second layer and an ANFIS interference controller (AIC) in the third layer. The design aim of the proposed three layer cascade ANFIS cognitive engine is maximizing the average throughput of the mobile wireless network, while minimizing the transmit power and interference power.

摘要翻译： 智能技术是执行网络资源管理的有效方法。 提出了一种基于智能控制器的三层级联自适应神经模糊推理系统（ANFIS）智能控制器，优化了多媒体呼叫业务的最大平均吞吐量，最小发射功率和干扰。 所提出的智能控制器设计有三层级联架构，主要包含第一层ANFIS速率控制器（ARC），第二层ANFIS功率控制器（APC）和第三层ANFIS干扰控制器（AIC） 层。 提出的三层级联ANFIS认知引擎的设计目标是最大化移动无线网络的平均吞吐量，同时最小化传输功率和干扰功率。