本文選題：深度學(xué)習(xí)　切入點：卷積神經(jīng)網(wǎng)絡(luò)　出處：《華中師范大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：近年來,在教育信息化背景下,人工智能、自然語言處理等技術(shù)日漸成熟,越來越多的數(shù)學(xué)題目以電子文檔的形式呈現(xiàn)的迫切需求,探索教育信息化環(huán)境下學(xué)生自主創(chuàng)新學(xué)習(xí)的新模式,輔助學(xué)生提高數(shù)學(xué)問題的解決能力,為學(xué)習(xí)者提供智能化的教育服務(wù)已成為必然趨勢。四則運算在數(shù)學(xué)計算中起著關(guān)鍵性作用,實現(xiàn)四則運算的智能解答是機器自動求解數(shù)學(xué)題目的基礎(chǔ),可以為教育信息化環(huán)境下學(xué)生的自主學(xué)習(xí)提供個性化輔導(dǎo)。構(gòu)建四則運算題目的智能解答模型,可以為數(shù)學(xué)運算、合并同類項、求解方程式等題目的機器自動解答提供技術(shù)支持和參考。而四則運算題目的智能解答的核心在于四則運算式中運算符的識別,本項研究針對智能解答系統(tǒng)中的四則運算符識別問題,以深度學(xué)習(xí)為切入點,采用基于字符級的編碼方式,訓(xùn)練CNN,形成了四則運算符識別的網(wǎng)絡(luò)模型,并通過實驗驗證了其有效性。本項研究主要包括四個方面:第一,算法架構(gòu)的搭建,構(gòu)建了神經(jīng)網(wǎng)絡(luò)和卷積神經(jīng)網(wǎng)絡(luò)。并設(shè)置好卷積神經(jīng)網(wǎng)絡(luò)模型的卷積、池化等提取特征方法,以及卷積神經(jīng)網(wǎng)絡(luò)中隱藏層的層數(shù)及每個隱藏層對應(yīng)的節(jié)點數(shù)。第二,設(shè)置編碼和字符量化的規(guī)則。根據(jù)字符量化規(guī)則,使用One-hot編碼方法對實驗數(shù)據(jù)進(jìn)行編碼處理,將輸入數(shù)據(jù)轉(zhuǎn)換為一個一維向量。第三,生成實驗數(shù)據(jù),從加減乘除四個維度分別生成三種類型的數(shù)學(xué)四則運算式數(shù)據(jù)集,包括訓(xùn)練集、驗證集、測試集。第四,將編碼后向量化的數(shù)據(jù)集分別輸入到設(shè)計好的兩個網(wǎng)絡(luò)中,從訓(xùn)練中學(xué)習(xí)運算符識別的“經(jīng)驗”。并使用測試數(shù)據(jù)集和預(yù)測數(shù)據(jù)檢驗了識別效果。目前,將深度學(xué)習(xí)技術(shù)與機器自動求解相融合的大量的科研工作均是基于詞的文本分類研究,而本項研究采用的是字符級的字符編碼識別,通過實驗驗證了網(wǎng)絡(luò)的有效性,生成了四則運算符識別的網(wǎng)絡(luò)模型,相比傳統(tǒng)神經(jīng)網(wǎng)絡(luò)的接近100%的識別率,深度卷積網(wǎng)絡(luò)的正確識別率達(dá)到了 100%。并用隨機生成的預(yù)測集進(jìn)行了預(yù)測,預(yù)測完全正確,達(dá)到了數(shù)學(xué)四則運算符的識別目的。
[Abstract]:In recent years, under the background of educational information, artificial intelligence, natural language processing and other technologies are becoming more and more mature, and more and more mathematical problems are presented in the form of electronic documents. To explore a new model of students' independent and innovative learning under the environment of educational information, to assist students to improve their ability to solve mathematical problems, It has become an inevitable trend to provide intelligent educational services for learners. Four principle operations play a key role in mathematical calculation, and the intelligent solution of the four principles is the basis for the machine to solve mathematical problems automatically. It can provide individualized tutoring for students' autonomous learning in the information environment of education. The machine automatic solution to the problems such as equations provides technical support and reference. The core of the intelligent solution of the four principle operation problems lies in the identification of operators in the four principles. In order to solve the problem of the recognition of the four principle operators in the intelligent solution system, this research takes the deep learning as the breakthrough point, uses the coding method based on the character level, trains the CNN, and forms a network model of the recognition of the four arithmetic operators. This research mainly includes four aspects: firstly, the structure of the algorithm, the neural network and the convolution neural network are constructed, and the convolution neural network model is set up. In addition, the number of hidden layers and the number of nodes corresponding to each hidden layer in the convolutional neural network. Secondly, the rules of encoding and quantization are set, and the rules of character quantization are used according to the rules of character quantization. The experimental data is encoded by One-hot coding method, and the input data is converted into a one-dimensional vector. Thirdly, the experimental data is generated, and three types of mathematical four-principle expression data sets are generated from the four dimensions of addition, subtraction, multiplication and division, respectively. Including the training set, the verification set, the test set. 4th, the encoded vectorized data sets are respectively input into the two networks designed. Learn the "experience" of operator recognition from the training. And test the recognition effect using test data sets and predictive data. A great deal of research work that combines depth learning technology with machine automatic solution is based on text classification of words, and this research adopts character level character coding recognition, and the effectiveness of the network is verified by experiments. The network model of four arithmetic operators is generated. Compared with the traditional neural network, the recognition rate of the deep convolution network is close to 100%, and the correct recognition rate of the deep convolution network is 100. The prediction is completely correct by using the randomly generated prediction set. The recognition purpose of mathematical four arithmetic operators is achieved.
【學(xué)位授予單位】：華中師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：G623.5;G434

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 渠新峰;;海量數(shù)據(jù)機器單詞中關(guān)鍵語義篩選方法研究[J];現(xiàn)代電子技術(shù);2017年06期

2 魏雪峰;李逢慶;鐘靚茹;;2015年度國際教育信息化發(fā)展動態(tài)及趨勢分析[J];中國電化教育;2016年04期

3 張晴晴;劉勇;潘接林;顏永紅;;基于卷積神經(jīng)網(wǎng)絡(luò)的連續(xù)語音識別[J];工程科學(xué)學(xué)報;2015年09期

4 杜金華;張萌;宗成慶;孫樂;;中國機器翻譯研究的機遇與挑戰(zhàn)——第八屆全國機器翻譯研討會總結(jié)與展望[J];中文信息學(xué)報;2013年04期

5 孫志軍;薛磊;許陽明;王正;;深度學(xué)習(xí)研究綜述[J];計算機應(yīng)用研究;2012年08期

6 趙志宏;楊紹普;馬增強;;基于卷積神經(jīng)網(wǎng)絡(luò)LeNet-5的車牌字符識別研究[J];系統(tǒng)仿真學(xué)報;2010年03期

7 喬維高;徐學(xué)進(jìn);;無人駕駛汽車的發(fā)展現(xiàn)狀及方向[J];上海汽車;2007年07期

，

本文編號：1617951