單組訓練法 的英文怎麼說

中文拼音 [dānzǔxùnliànfǎ]
單組訓練法 英文
single set system
  • 組 : Ⅰ名詞1 （由不多的人員組成的單位） group 2 （姓氏） a surname Ⅱ動詞（組織） organize; form Ⅲ量詞（...
  • 訓 : Ⅰ動詞1 （教導; 訓誡） lecture; teach; train 2 （解釋） explainⅡ名詞1 （準則） standard; model; ex...
  • 練 : Ⅰ名詞1 （白絹） white silk 2 （姓氏） a surname Ⅱ動詞1 （加工處理生絲） treat soften and whiten s...
  • 法 : Ⅰ名詞1 （由國家制定或認可的行為規則的總稱） law 2 （方法; 方式） way; method; mode; means 3 （標...
  • 訓練 : train; drill; manage; practice; breeding
  1. This article puts forward a solution named divide - assemble by deducing the size of bp neural network to overcome entering the local best point, the dividing process is that a big bp neural network is divided into several small bp neural networks, every small bp neural network can study alone, after all small bp neural networks finish their study, we can assemble all these small bp neural networks into the quondam big bp neural networks ; on the basis of divide - assemble solution, this article discusses the preprocessing of input species and how to deduce the size of bp neural network further to make it easy to overcome entering the local best point ; for the study of every small bp neural network, this article adopts a solution named gdr - ga algorithm, which includes two algorithms. gdr ? a algorithm makes the merits of the two algorithms makeup each other to increase searching speed. finally, this article discusses the processing of atm band - width distribution dynamically

    本文從bp網的結構出發，以減小bp神經網路的規模為手段來克服陷入局部極小點，提出了bp神經網路的拆分組裝方法，即將一個大的bp網有機地拆分為幾個小的子bp網，每個子網的權值單獨訓練，訓練好以後，再將每個子網的單元和權值有機地組裝成原先的bp網，從理論和實驗上證明了該方法在解決局部極小值這一問題時是有效的；在拆分組裝方法基礎上，本文詳細闡述了輸入樣本的預處理過程，更進一步地減小了bp網路的規模，使子網的學習更加容易了；對于子網的學習，本文採用了最速梯度? ?遺傳混合演算法（即gdr ? ? ga演算法） ，使gdr演算法和ga演算法的優點互為補充，提高了收斂速度；最後本文闡述了用以上方法進行atm帶寬動態分配的過程。
  2. According to objective orientation, the authors offered the following suggestions : in terms of routine setup, we should base the main contents on the essential combos of representative martial arts carefully selected, and base the initial posture, ending posture and transitional posture on the exclusive chinese fist clenching courtesy ; in terms of routine training, we should seek for the power of expression, and concurrently take care of move standardization as well as offense and defense awareness ; in terms of teaching, we should adopt the mode of learning single move techniques and combo move techniques first, then doing an antagonistic exercise, and finally putting series moves into a complete routine

    根據目標定位，建議在套路編排方面，以精選的代表性拳種的精華組合為主要內容，以中國獨有的抱拳禮為起收勢和銜接點；在套路訓練方面，以求取勁力為立足點，併兼顧動作的規范和攻防意識；在教學方面，採用先進行單勢技法、組合技法學習，再進行對抗性練習，最後進行套路串接的模式。
  3. In course of training the network, the structure of the network has been analysed. using the nonlinear theory, the node of the hidden layer is ascertained. by comparing this method is very efficient

    （ 5 ）在網路訓練過程中，對神經網路結構進行了分析，建立了計算輸出和理想輸出關系非線性方程組，依據非線性方程理論闡述設計變量、樣本數量和輸出層單元數量的關系，確定了隱層神經元的數量，經比較該方法很有效。
  4. The output information of single classifier has three forms of abstract, rank and measurement single classifier supplies both the unknown pattern classifying information on the measurement level and the wrong classifying distribution information of the training samples on the abstract level, which are used to design the fuzzy multiple classifiers combination method

    單個分類器的輸出信息有三種表現形式：符號層、排序層、度量層。應用單個分類器在度量層次上，對未知模式的分類信息；在符號層次上，訓練樣本的錯分類分佈狀況，設計了模糊多分類器組合方法。
  5. It solves these problems by using neural network based on fuzzy decison and neural network group. compared with traditional network, neural network based on fuzzy decison has simple structure, clear logic layer and short training time, while for network group, it is more intelligence and fuses uncertain information better without longer training time

    就此本文提出了基於模糊決策的神經網路和帶有加權融合的神經網路組兩種目標識別方法，與傳統的神經網路相比，基於模糊決策的神經網路結構簡單，邏輯層次分明，學習訓練演算法簡潔，而神經網路組在不增加訓練時間的基礎上，提高了網路的智能特性，能夠更加合理地對不確定性信息進行融合。
  6. This text realizes optimal linear combination method basing on recognition confidence. this method advances recognition confidence scaling recognition performance for each sample. in train phase divide train samples into different areas with their recognition confidence and apply olc in different areas to get multi - classifier combination power vector

    此方法提出了用於衡量分類器對單個樣本識別性能的判決可靠度，在訓練階段根據各分類器的判決可靠度把訓練樣本分成不同的區域，從而可以在不同的區域里應用最優線性集成方法得出各區域的分類器組合權值。
分享友人
分享到 Line

分享到臉書