機率學習 的英文怎麼說
中文拼音 [jīlǜxuéxí]
機率學習
英文
probability learning（pl）-
In this paper, we study the trading model based on the project " the network market ", which was implemented by the chongqing electronic commerce inc and us. aiming at the shortage of trading model in " the network market ", we employ game theory and multi - criteria decision theory, introduce the matchmaking schema based on price and quantity into electronic commerce application, bring forward a market matchmaking trading model including five phases : market matchmaking, reinforce learning, biliteral negotiation, contract signing, contract executing. the main work and conclusion as follows : considering the behaviour of multi - buyers with multi - sellers, we realise a matchmaking model based on the price and quantity through double auction mechanism under discriminatory and non - discriminatory price situation, analyse the incentive compatibility and competitive equilibrium of the mechanism
主要研究成果如下:針對多個買家與多個賣家的交易行為，提出一種撮合交易模型?採用價格和數量作為撮合要素，以雙重拍賣機制為撮合手段，重點研究均價和差價形式下的實現機制，並對其激勵相容性和市場均衡進行理論分析?為增強市場效率，論文提出了一種針對雙重拍賣的學習機制，它以三參數學習模型為基礎進行改進，藉助交易歷史信息，實現交易代理的自我學習Procreant knowledge expression and forward inference engine are adopted in the method of fault diagnosis based on expert system theory. in the fault diagnosis applying neural network theory, six kinds of improved arithmetic of back - propagation arithmetic, including gradient descent with momentum, variable learning rate back - propagation, resilient back - propagation, quasi - newton, levenberg - marquardt and conjugate gradient, are applied to diagnose the faults of electric load manage center and solid state power controller. different diagnostic results gotten by simulation are compared at last
在基於專家系統的故障診斷方法中，採用了產生式知識表達和正向推理機制；在基於神經網路的故障診斷方法中，則分別採用了bp神經網路的附加動量法、自適應學習速率、彈性bp演算法、擬牛頓法、共軛梯度法和levenberg - marquardt法對電氣負載管理中心和固態功率控制器的故障進行診斷，並對由模擬得到的不同診斷結果進行比較。The modern technology give a chance for the pattern of transmitting knowledge with network, the course based on network have opened up it ' s way in china, our pursuer paid more attention to the mode, but in america, pursuer have studied the more width aspect, thereinto the investigation and design of the information in the course based on network is very important, for the design of the information decide the pattern how the student receive the information, which will effect the way of knowledge understanding and memory, and the way is related to the study pattern, so the design of the information in the course based on network is very important to the efficiency and effect. so the core of the paper is the investigation and design of the information in the course. i have the entropy from the information science as the analyse tool to analyse the information, these work tell us the efficient pattern to transmit information, based on the result, i design the net page, of course, study theory and the character of the net itself are also the factors i employ for design a good net page. then, links and navigation is constituted for students adapt to the course based on network
當今技術的發展給知識以網路為媒介來傳播的學習方式帶來前所未有的機遇，網路課程在國內迅速開展起來，但是國內研究者的注意力主要集中在對網路課程模式的探索上，放眼國外，他們的研究觸角已經涉及到網路課程比較細致的方面，尤其是對網路課程信息的研究構成了國外網路課程研究中的比較重要的一個方面，而網路課程中信息的設計是重要的，因為信息的組織設計是為了接受者能對信息進行有效的信息加工，信息的呈現模式影響著學習者對知識的理解和記憶方式，進而決定了學習者的學習模式，因此網路信息的設計在網路課程傳遞的效率和效果中就佔有很重要的位置。基於這個觀念，本文把網路信息的組織設計作為研究的重點，引入了信息科學作為研究的主要工具對網路中的信息作以量化分析研究，主要應用了信息科學中信息熵的公式進行推導，得到學習內容信息組織的基本模式，並充分利用網路自身特性和學習理論對知識信息進行細致的設計，此外還對鏈接和導航信息進行了設計，在網路課程的適應性方面作出了努力，把交互信息與輔助學習信息的分析設計與應用和對網路頁面信息的總體調節優化作為主體信息設計部分的補充，最終形成了網路信息組織設計的方案，力求創設一個能夠有效傳遞知識信息，減少網路自身弊病，並帶有一定適應性的網路學習環境，也使更多的網路課程的設計者關注網路信息這個因素。In experiment of computer constitute principle, using multimedia teach of experiment, to do strengthen understand of exoterica knowledge, to do advance efficence of study and adbilite of resolve question to do ground of development
摘要在計算機組成原理實驗課程中，利用多媒體進行實驗教學，能增強學生對理論知識的理解，提高學生學習的效率和解決實際問題的能力，為學生今後的發展打下堅實的基礎。Network forensics is an important extension to present security infrastructure, and is becoming the research focus of forensic investigators and network security researchers. however many challenges still exist in conducting network forensics : the sheer amount of data generated by the network ; the comprehensibility of evidences extracted from collected data ; the efficiency of evidence analysis methods, etc. against above challenges, by taking the advantage of both the great learning capability and the comprehensibility of the analyzed results of decision tree technology and fuzzy logic, the researcher develops a fuzzy decision tree based network forensics system to aid an investigator in analyzing computer crime in network environments and automatically extract digital evidence. at the end of the paper, the experimental comparison results between our proposed method and other popular methods are presented. experimental results show that the system can classify most kinds of events ( 91. 16 ? correct classification rate on average ), provide analyzed and comprehensible information for a forensic expert and automate or semi - automate the process of forensic analysis
網路取證是對現有網路安全體系的必要擴展，已日益成為研究的重點.但目前在進行網路取證時仍存在很多挑戰:如網路產生的海量數據;從已收集數據中提取的證據的可理解性;證據分析方法的有效性等.針對上述問題，利用模糊決策樹技術強大的學習能力及其分析結果的易理解性，開發了一種基於模糊決策樹的網路取證分析系統，以協助網路取證人員在網路環境下對計算機犯罪事件進行取證分析.給出了該方法的實驗結果以及與現有方法的對照分析結果.實驗結果表明，該系統可以對大多數網路事件進行識別（平均正確分類率為91 . 16 ? ） ，能為網路取證人員提供可理解的信息，協助取證人員進行快速高效的證據分析The thesis analyzed the present transferring status between pudong airport and shanghai " s incity. through forecasting the long - dated flux of pudong airport and the area near it and combining the planning scheme of shanghai urban rapid mass transit, the thesis learned the helpful experience of the traffic organization in typical airport abroad and used the scientific analyzing model of public traffic flux forecasting to put forward some reasonable suggestion of the bottleneck question between pudong airport and incity : the one is to use the present no. 2 subway as the future airtrain to take on the most part of the flux and meantime present the concept of feeder efficiency to quantitative analyze the choice of feeder station ; the other is to set up cat ( city air terminal ) to convenient the passenger to come airport rapidly and economically in order to lessen the pressure of the traffic and improve the whole service quantity of civil aviation transportation
本文分析了浦東機場與市內目前的換乘現狀，從預測浦東機場及緊鄰空港區域中遠期的客流量入手，結合上海市政府快速軌道交通的規劃方案，並且學習境外典型機場交通組織的有益經驗，利用規劃中的公交客流預測等科學分析模型，對浦東機場與市中心的軌道交通銜接提出了合理的建議：一是利用目前的地鐵二號線作為航空軌道共享線來承擔大部分進出空港的客流，並且給出了以接運效率最大化為目標函數的接運公交軌道站點比選模型；二是在市中心設立城市航站樓以方便旅客快速、經濟地到達機場，從而減少道路交通壓力，提高航空運輸的整體服務質量。The second is that monopoly produces some positive effects : as static efficiency to say, there are four mechanisms, namely economies of scale, economies of scope, internalization of externalities and learning effect, which optimize the allocation of resources. monopoly advantages decrease of transaction cost. some extent monopoly has benefits to technology innovation and human capital accumulation
其次，壟斷具有正的效應：從靜態效率來看，壟斷存在四種優化資源配置的機制（規模經濟機制、范圍經濟機制、外部性內化機制和學習效應機制） ；壟斷有利於機會成本的降低，從而可以提高社會經濟活動的效率；從動態效率來看，一定程度的壟斷有利於技術進步和人力資本的積累，因而是動態有效的。In rational selecting talent for the job, we must abolish the ideas such as " attaching importance to diploma only ", learning " can be postponed ", " arranging posts according to longevity " and " demanding perfection ", set up the new ideas such as " attaching importance to actual achievement ", " stressing efficiency ", " arranging posts according to ability " and " making use of individual speciality ", and set up the new mechanism of talent thriving enterprise, that is : to set up the talent selecting mechanism that accords with modem enterprise system requirement, learning and developing type personnel training mechanism, talent appraisement mechanism that achievement and efficiency have priority, the talent encouraging and restricting mechanism that integrates market
在合理用人方面，我們必須破除「唯文憑論」 、學習「可遲可緩」 、 「論資排輩」 、 「求全責備」等觀念，樹立「注重實績」 、 「講求效率」 、 「唯才是舉」 、 「用其所長」的新觀念，構建人才強企的新機制，即：構建符合現代企業制度要求的人才選用機制、學習開發型的人才培養機制、績效優先的人才評價機制、與市場接軌的人才激勵約束機制。Chapter four a transfer view on experiment in physics teaching this chapter is trying to discuss the reason leading to the students " positive transfer in their physical experiment studying in the light of principles of elicitation and independent experiment, principles of discovery and characteristic experiment, principles of methodology and experimental skills, principles of approximation and experiment efficiency, and principles of reflection and experiment extension, these five aspects
第四章物理實驗教學的遷移觀本章從啟發性原則與獨立實驗、發現法原則與個性實驗、方法性原則與實驗技能、隨機性原則與實驗效率、反思性原則與實驗延伸等五個方面加以討淪，努力促全韭學生物理實驗學習的積極遷移。Because ga possesses the traits of can global random search, the robustness is strong, been use briefly and broadly, it didn ’ t use path search, and use probability search, didn ’ t care inherence rule of problem itself, can search the global optimum points effectively and rapidly in great vector space of complicated, many peak values, cannot differentiable. so it can offset the shortages of nn study algorithm, can reduce the possibility that the minimum value get into local greatly, the speed of convergence can improve, interpolation time shorten greatly, the quantity of training reduce
因為遺傳演算法具有全局隨機搜索能力，魯棒性強、使用簡單和廣泛的特點，它不採用路徑搜索，而採用概率搜索，不用關心問題本身的內在規律，能夠在復雜的、多峰值的、不可微的大矢量空間中迅速有效地尋找到全局最優解，所以可以彌補神經網路學習演算法的不足，使陷入局部最小值的可能性大大減少，使得收斂速度提高，訓練量減小。Just as most of the natural language process technologies, the methods of ner have two classes, statistic - based and rule - based. considering of the limitation of using only one of the methods, we combined both of the methods to recognize named entity in this thesis. we combined the maching learning with ner to make the system get the ability of self - learning. we have done research on decision tree of maching learning mainly and designed a recognize model to recognize named entity. this model first used the probability and statistic way to extract the potential named entities, and then some context linguistic language information are employed in the model to recognize the named entities furtherly. as the wrong entites are denied, the recongnize effect has been improved
鑒于單獨採用基於統計方法或基於規則方法的缺陷，在這篇論文中，採用了統計與規則相結合的方法來識別命名實體。為了使系統具有學習能力，我們把機器學習方法應用於中文命名實體的識別，這里我們著重研究了機器學習中的決策樹方法在中文命名實體識別中的應用;設計了一種基於決策樹的識別模式，該模式首先利用概率統計方法，在文本中盡量完備地識別出潛在的命名實體，然後利用潛在命名實體相關的上下文詞法、語法和語義特徵作為屬性構建決策樹，否定不正確的實體，進一步提高了命名實體識別的準確率。Comparing with non - bnyain methods, it ' s prominent featares lay in that it combines the prior and posterior information, which avoids the disadvantag of subjective bias caused by simply using the prior information only, of blind search caused by the incomplete sample information, of noise affection caused by simply using the sample information only if we choice a suitable priof, we can conduct the bayesian leaming effectively, so it fits the problems of data mining and machine leaming that possess charaters of probability and statistics, especially when the samples are rare
與非貝葉揚方法相比，貝葉斯方法的特出特點是其學習機制可以綜合先驗信息和后驗信息，既可避免只使用先驗信息可能帶來的主觀偏見，和缺乏樣本信息時的大量盲目搜索與計算，也可避免只使用樣本信息帶來的噪音的影響只要合理地確定先驗，就可以進行有效的學習。因此，適用於具有概率統計特徵的數據採掘和機器學習（或發現）問題，尤其是樣本難得的問題Firstly, the backgrounds and techniques of intrusion detection system ( ids ) are introduced briefly in this paper, also the current status. then an intrusion detection system based on a new nonstationary machine learning technique model is presented and improved. on the precondition of the same false alarm rates, more intrusions have been detected, and less time for detection is needed with the improved system
本文首先引入了一種基於機器學習規則的、用於入侵檢測系統的動態模型，並對該模型加以改進，在誤警率不變的前提下，使系統能夠檢測到更多的入侵種類，縮短了系統檢測時間，從而提高了系統性能。My thesis focuses on analysis network audit data using data mining, and mine rules about intrusion detection. intrusion detection efficiency is improved by using machine learning methods, thereby enhance adaptation of intrusion detection
本文主要從數據挖掘的角度對網路數據進行分析，發掘出入侵檢測的模型，用機器學習的理論改進入侵檢測的效率，提高入侵檢測的自適應性。Because of ineffectiveness of naive bayes model for text classification, this thesis proposed integrating boosting theory of machine learning in classification process, boost naive bayes categorization model through many times training. improved by experiments, mutual information and naive bayes integrated with boosting bring very good precision, recall, and f1 score
鑒于樸素貝葉斯的分類效果不佳，本論文又提出將機器學習中的boosting思想結合到樸素貝葉斯的分類模型中，對樸素貝葉斯模型進行提升，實驗證明，改進的互信息和給合了boosting思想的樸素貝葉斯分類模型均產生良好的分類效果?分準率、分全率及f1值。They are agricultural productive materials price growth rate, sown area of grain crops growth rate, grain yield per area growth rate -, natural disaster covered grain areas growth rate, net grain import change rate, grain reserve change rate, population growth rate, per income growth rate, city and town population growth rate, food industry production value growth rate, year - end pig number growth rate, medical & pharmaceutical and textile industry production value growth rate, grain marketization degree, inflation rate using the previous year as base year ( preceding year = 100 ), public grain purchases price growth rate, investment in agricultural science and technology growth rate, investment in agricultural infrastructure growth rate, growth rate of graduates number from agriculture, forestry, science & technology universities and colleges and specialized secondary schools, government expenditure for agriculture and agricultural credit growth rate, international grain price growth rate, rmb exchange rate growth rate, last grain price growth rate, economic crop price growth rate, meanwhile, a new method is attempted to be used in this paper and the grain price early - warning problem is transformed into machine learning problem by introducing statistic learning theory and svm method which are gaining popularity in machine learning field at present in the world
在此基礎上，篩選出23個警兆指標：農用生產資料價格增長率、糧食播種面積增長率、糧食單產增長率、糧食受災面積增長率、糧食凈進口量變化率、糧食儲備變動率、人口增長率、人均收入增長率、城鎮人口增長率、食品工業產值增長率、豬年末頭數增長率、醫藥紡織工業產值增長率、糧食市場化程度、以上年為基年的通貨膨脹率、國家糧食定購價格增長率、農業科技投入增長率、農業基礎設施投入增長率、農、林、科技高校大、中專畢業生人數增長率、財政支農資金比重及農業信貸增長率、國際糧食市場價格增長率、人民幣匯率增長率、上期糧食價格增長率、經濟作物價格增長率。同時論文在預警方法上作了新的嘗試，把糧食價格預警問題轉換成一個機器學習問題，引進當前國際上機器學習領域中比較熱門的統計學習理論和支持向量機方法，用順序回歸演算法對歷史數據進行學習建立了糧食價格預警模型。Memorization of information by frequency repetition ( rote learning ) plays a role in education system to what extend do you agree or disagree
信息的記憶來自重復的頻率，那麼機械學習扮演了一個重要角色在教育體系中！你同意嗎？In order to withstand more and more frequent compound network attacks and hacker commitment of distribution, multiobjective, multistage nowadays, improve intrusion detection efficiency under the circumstance of high band width and large - scale network, decrease false negative rate and shorten detection time, incorporating advanced machine learning techniques into ids is already a well - known thought
為了對付目前越來越頻繁出現的分散式、多目標、多階段的組合式網路攻擊和黑客行為，提高在高帶寬、大規模網路環境下入侵檢測的效率、降低漏報率和縮短檢測時間，把先進的機器學習方法引入到ids中來已成為一種共識。The metal mechanism of high - efficiency learning
高效率學習的心理機制研究We try the unsupervised wsd method based on equivalent pseudowords by the na ? ve bayes model and maximum entropy in paper. it gets 81 % correct rate on the test data of senseval - 3, which is obvious better than supervised method accordingly
利用得到的兩種較優的機器學習方法:貝葉斯模型及最大熵模型，本文嘗試了基於等價偽詞的無指導詞義消歧方法，在senseval - 3的測試數據上獲得了81 %的正確率，明顯優于相應的有指導方法。分享友人