智能学习 meaning in Chinese
intellectual learning
intelligence learning
intelligent learning
Examples
- Development of intelligent air - conditioning and refrigeration designing software for study
具有智能学习功能的空调制冷系统设计软件的开发 - I analyze the request of curriculum arrangement , using intellect learning arithmetic ' s q - learning , designing an applied mathematics model to deal with this problem
本文对大学课表的排课要求进行了全面的分析，结合智能学习算法的q学习算法，设计出了课表编排问题的较为实用的模型。 - Self feed back model that adopt fuzzy deduce technology and fuzzy integrate judge mechanism is introduced in this article , it is the kernel function model of intelligent instruction system
论文的自反馈模型采用以模糊数学为基础的模糊推理技术和模糊综合评判机制，是智能学习系统的核心功能模块。 - Therefore , self feed back model is a key technique to meet the demand of individual intelligent instruction system , and will be a stubborn base to make individual distance education popularize ^ spread and practice
自反馈模型较好解决了智能学习系统个性化要求的关键技术，为个性化远程教育的普及与更好的推广、实施打下了基础。 - In the algorithm level , currently various training algorithms of neural networks , including gradient algorithms , intelligent learning algorithms and hybrid algorithms , are comparatively studied ; the optimization principle of bp algorithm for neural networks training is analyzed in detail , and the reasons for serious disadvantages of bp algorithms are found out , moreover , the optimization principle of two kinds of improved bp algorithms is described in a uniform theoretic framework ; and the global optimization algorithms of neural networks , mainly genetic algorithm are expounded in detail , it follows that a improved genetic algorithm is proposed ; finally the training performances of various algorithms are compared based on a simulation experiment on a benchmark problem of neural network learning , furthermore , a viewpoint that genetic algorithm is subject to " curse of dimension " is proposed
在算法层，本文对目前用于神经网络训练的各种算法，包括梯度算法、智能学习算法和混合学习算法进行了比较研究；对用于神经网络训练的bp算法的优化原理进行了详细的理论分析，找到了bp算法存在严重缺陷的原因，并对其两类改进算法-启发式算法和二次梯度算法的优化原理，在统一的框架之下进行了详尽的理论描述；对神经网络全局优化算法主要是遗传算法进行了详细的阐述，并在此基础上，设计了一种性能改进的遗传算法；最后基于神经网络学习的benchmark问题对各种算法在网络训练中的应用性能进行了仿真研究，并提出了遗传算法受困于“维数灾难”的观点。