搜索结果: 1-12 共查到“人工智能 method”相关记录12条 . 查询时间(0.14 秒)
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Distributed sparse identification theory and method
分布式 稀疏识别 理论方法
font style='font-size:12px;'>
2023/11/29
In this talk, we will consider the distributed sparse identification problem over wireless sensor networks such that all sensors cooperatively estimate the unknown sparse parameter vector of stochasti...
New tool helps people choose the right method for evaluating AI models（图）
AI模型 行为方式 机器学习模型 人工智能
font style='font-size:12px;'>
2023/6/20
When machine-learning models are deployed in real-world situations, perhaps to flag potential disease in X-rays for a radiologist to review, human users need to know when to trust the model’s predicti...
A method for designing neural networks optimally suited for certain tasks（图）
神经网络 机器学习模型 计算机网络
font style='font-size:12px;'>
2023/6/20
Neural networks, a type of machine-learning model, are being used to help humans complete a wide variety of tasks, from predicting if someone’s credit score is high enough to qualify for a loan to dia...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：A LASSO-based Detection and Identification Method on Actuator Integrity Attacks in Remote Control Systems
LASSO 远程控制系统 执行器 完整性 攻击检测 识别方法
font style='font-size:12px;'>
2023/4/28
We consider actuator attacks in a remote control system. Compared with sensor attacks that have been studied in most existing literature, the malicious attacks over actuators can cause more disastrous...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：A two-stage physics-informed neural network method based on conserved quantities and applications in localized wave solutions
守恒量 两阶段物理信息 神经网络方法 局部波解
font style='font-size:12px;'>
2023/5/5
With the advantages of fast calculating speed and high precision, the physics-informed neural network method opens up a new approach for numerically solving nonlinear partial differential equations. B...
Busy GPUs: Sampling and pipelining method speeds up deep learning on large graphs（图）
GPU 流水线 大型图形 深度学习
font style='font-size:12px;'>
2023/6/20
Graphs, a potentially extensive web of nodes connected by edges, can be used to express and interrogate relationships between data, like social connections, financial transactions, traffic, energy gri...
FEATURE VECTOR CONSTRUCTION METHOD FOR IRIS RECOGNITION
Iris recognition Iris feature extraction Biometrics Mobile biometrics Quantization Encoding
font style='font-size:12px;'>
2017/6/19
One of the basic stages of iris recognition pipeline is iris feature vector construction procedure. The procedure represents the extraction of iris texture information relevant to its subsequent compa...
A State Estimation Method for Sound Environment System with Unknown Observation Mechanism by Introducing Fuzzy Inference
State Estimation Sound Environment System Unknown Observation Mechanism Fuzzy Inference
font style='font-size:12px;'>
2013/1/28
The observed phenomena in real sound environment system often contain uncertainty such as the additional external noise with unknown statistics. Furthermore, there is complex nonlinear relationship be...
A New Numerical Method for Solving the Stokes Problem Using Quadratic Programming
Galerkin Method Neural Network Model Quadratic Programming Problem Stokes Problem
font style='font-size:12px;'>
2013/1/28
In this paper we present a new method for solving the Stokes problem which is a constrained optimization method. The new method is simpler and requires less computation than the existing methods. In t...
基于改进Harris角点提取的摄像机神经网络标定技术（Neural Network Technique on Camera Calibration Based on Improved Harris Corner Extraction Method）
摄像机标定 神经网络 Harris角点
font style='font-size:12px;'>
2009/9/11
以前馈型BP神经网络进行双目立体视觉系统的摄像机标定研究，基于Harris角点提取，提出了增加约束的改进方法，从而提高网络训练样本集的数据精度；探讨了神经网络的欠泛化、过泛化问题，综合运用归一化、提前终止等多种策略，进一步提高网络泛化能力，并与经典标定方法进行对比。试验结果表明，该方法能够获得较高的摄像机标定精度。
A NOVEL FEATURE EXTRACTION METHOD FOR ISOLATED WORD RECOGNITION BASED ON NESTED TEMPORAL AVERAGING
Speech recognition Pattern classification Neural Networks Support Vector Machines
font style='font-size:12px;'>
2010/1/12
A novel preprocessing method is proposed. It has a reduced complexity and therefore is aimed to be used in low power, VLSI implemented, speech recognizers. Our algorithm extracts a feature vector made...
AN ICA BASED METHOD FOR TEXTURE RECOGNITION
Independent Component Analysis Negentropy Pattern Recognition
font style='font-size:12px;'>
2010/1/12
The method proposed in this paper uses the Independent Component Analysis (ICA) for an application of unsupervised recognition of textures. The analysed texture is modelled by a weighted sum of almost...