次梯度的英文

• subgradient

• "次"英文翻译    order; sequence
• "梯度"英文翻译    gradient; grad
• "次梯度风" 英文翻译 :    subgradient wind
• "多层次梯度回波序列" 英文翻译 :    multiple-slice-gradient-echo sequence
• "梯度" 英文翻译 :    [物理学] gradient; [数学] grad
• "势梯度，位梯度" 英文翻译 :    potential gradient
• "位梯度；势梯度" 英文翻译 :    potential gradient
• "ph梯度" 英文翻译 :    ph gradient
• "场梯度" 英文翻译 :    field gradient
• "超梯度" 英文翻译 :    supergradient
• "大梯度" 英文翻译 :    heavy gradient
• "倒梯度" 英文翻译 :    inverse gradient
• "电梯度" 英文翻译 :    electrical gradients
• "陡度，梯度" 英文翻译 :    gradient
• "陡梯度" 英文翻译 :    heavy gradient; steel gradient
• "反梯度" 英文翻译 :    antigradient; countergradient; upgradient
• "负梯度" 英文翻译 :    antigradient; negative gradient
• "高梯度" 英文翻译 :    high gradient
• "角梯度" 英文翻译 :    angular gradient
• "力梯度" 英文翻译 :    force gradient
• "零梯度" 英文翻译 :    zero gradient
• "内梯度" 英文翻译 :    inside gradient
• "热梯度" 英文翻译 :    heat gradient; temperature gradient; thermal gradient; tone'smal gradient
• "势梯度" 英文翻译 :    potential gradient
• "碳梯度" 英文翻译 :    carbon gradiect

• 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。