提出了一种用于修正光学神经网络硬件系统误差的虚拟神经网络模型。
The optical experimental results show that the virtual network can efficiently correct the errors of hardware system.
提出了一种用于修正光学神经网络硬件系统误差的虚拟神经网络模型。
A virtual neural network model for correcting the errors of hardware system is proposed.
本文给出了用人工神经网络硬件构成的汽门控制器的适应性实验结果,控制器采用BP网络离线训练。
The result of adaptability experiment for valving controller based on artificial neural network is presented in this paper. The controller is trained by off-line BP network.
由于细胞神经网络具有高速并行运算、便于硬件实现等特点,因此这种方法在图像实时处理中也具有很大的潜力和应用前景。
Because the cellular neural networks are uniquely suitable for the high-speed parallel computation and easy to implement in hardware, this model has more potential in real-time image processing.
针对卫星姿态测量系统的硬件故障,应用人工神经网络进行故障检测与诊断,得到了较为满意的结果。
Artificial neural networks are proposed in this paper, which are used to detect and diagnose faults of hardware for the satellite attitude measurement system. The result is satisfied.
对服务机器人实施力控制,要求实时性较高,采用神经网络的硬件实现方式实施控制,才能使系统达到更好的性能。
Implementing force control for a service robot calls for high real-time characteristic. Using hardware neural network to implement control can achieve better performance.
研究了气动柔性手指智能控制策略的硬件实现,设计了气动柔性手指的神经网络控制器。
This paper focused on the hardware realization of flexible pneumatic finger's intelligent control strategy, and a flexible pneumatic finger's neural network controller was designed.
该神经网络模型结构简单,便于硬件实现。
The architecture of this neural network is relatively simple, and easily implemented by the hardware.
本研究课题就是以CAN总线系统硬件平台为基础,重点针对智能装载机铲装过程进行模糊神经网络控制研究。
It is aimed to make the Fuzzy Neural Network control research on the loading of the intelligent loader based on CAN-BUS control system.
张航。基于硬件实现BP神经网络的电子鼻设计[d]。成都:西南交通大学,2015。
Zhang H. Design of electronic nose based on hardware implementation of BP neural network [d]. Chengdu: Southwest Jiaotong University, 2015.
人工神经网络的特点是:结构简单、能够大规模并行、容易用硬件实现等。
Neural network possesses many of advantages : simple structure, easy implementation in hardware, the basic parallel computational architecture, etc.
控制系统的硬件采用了DSP芯片,以保证系统的实时性;软件采用了模糊-神经网络算法,以克服系统模型的不确定性。
DSP chip is applied in hardware design to ensure real-time performance of control system, and fuzzy-neural network algorithm is adopted to overcome uncertainness of control model.
神经网络的硬件实现常伴随反馈信号的延时,网络的应用需要对具有时滞反馈网络稳定性的充分研究。
The physical implementation of neural network follows delays of feedback signal and the application of network requires the study of the stability.
随着并行技术的日益成熟,在并行集群上以软硬件相结合的方式设计神经网络的重要性也不断提高。
With parallel technology having become more matured, the neural networks' design process of hardware and software combination is getting more importance in these days.
随着神经网络理论、应用研究的不断深入,作为有效实现神经网络的物质基础—神经网络的硬件实现已成为世界各国竞相研究、开发的高科技热点之一。
With the study of neural network theory and application, hardware realization-the physical material to implement neural network-has become one hot spot of high technology among so many countries.
该方法可以推广至更多类型的神经网络,为神经网络的硬件实现提供了可靠的基础。
The method can be extended to more types of neural networks, provide a reliable basis for the neural network hardware implementation .
该方法可以推广至更多类型的神经网络,为神经网络的硬件实现提供了可靠的基础。
The method can be extended to more types of neural networks, provide a reliable basis for the neural network hardware implementation .
应用推荐