public int get_max(int x,int y,int z){ int max; if(x>=y) { max = x; } else { max = y; } if( z>=x ) { max = z; } return max; }分析该程序段有何逻辑错误

时间: 2023-12-02 16:02:54 浏览: 82
该程序段存在逻辑错误,因为无论 z 的值是多少,最终返回的 max 值都是 z。这是因为在第二个 if 语句中,应该判断 z 是否大于当前的 max 值,而不是判断 z 是否大于等于 x,应该将 if 语句改为: ``` if (z >= max) { max = z; } ``` 这样才能保证返回的是三个参数中的最大值。
相关问题

public int get_max(int x,int y,int z){ int max; if(x>=y) { max = x; } else { max = y; } if( z>=max) { max = z; } return max; }(3) 设计1个测试数据,使得执行该测试时会执行到fault并触发error,但不会引起Failure;

根据程序的逻辑错误,我们可以设计一个测试数据,使得执行该测试时会执行到 fault 并触发 error,但不会引起 Failure。假设输入的三个参数分别为 1,2,3,那么根据程序的逻辑,执行到第二个 if 语句时,应该执行 if 代码块中的语句,即将 max 的值更新为 z,返回值应该为 3。但是实际上,正确的结果是应该返回 3,因为输入的三个数字中 3 最大。因此,执行该测试数据时会执行到 fault,并触发 error,但不会引起 Failure。 具体实现可以使用 JUnit 进行测试,测试代码如下: ``` @Test public void testGetMax() { int result = get_max(1, 2, 3); assertEquals(3, result); } ``` 在该测试中,我们期望函数返回 3,但实际上返回的是 2,因此会触发 AssertionError 异常,表示执行到了 error,但是并不会引起测试失败,因为我们预期函数会执行到 fault。

public int get_max(int Age1, int Age2,int Age3){ int max; if(Age1 >= Age2) { max = Age1; } else { max = Age2; } if( Age3 > Age1 ) { max = Age3; } return max; } (1)试分析该程序段有何逻辑错误;

该程序段的逻辑错误在于第二个if语句中判断条件应该是Age3 > max而不是Age3 > Age1。因为在第一个if-else语句中已经确定了max是Age1或Age2中的较大值,所以Age3应该和max进行比较,而不是和Age1进行比较。因此,应该将第二个if语句改为: if (Age3 > max) { max = Age3; } 这样才能正确地找出三个年龄中的最大值并返回。

相关推荐

优化这段代码template<typename T> class MyTemplateClass:public QObject { Q_OBJECT public: MyTemplateClass(const T& data) : m_data(data) { qRegisterMetaType<SP104>("SP104"); qRegisterMetaType<DP104>("DP104"); qRegisterMetaType<SP104_T>("SP104_T"); qRegisterMetaType<DP104_T>("DP104_T"); qRegisterMetaType<ME_NA104>("ME_NA104"); qRegisterMetaType<ME_NB104>("ME_NB104"); qRegisterMetaType<ME_NC104>("ME_NC104"); qRegisterMetaType<YK_SP104>("YK_SP104"); qRegisterMetaType<YK_DP104>("YK_DP104"); t_cache.setMaxCost(MAP_MAX); } QMap<QString,QVector<T>>t_map; QMap<QString,QVector<T>>old_map; QCache<QString,QVector<T>>t_cache; QVector<T>t_vctor; QDateTime start_time; int state_flg; int expect_timedif; void set_firstaddr(int yxaddr,int ycaddr) { m_yxAddr = static_cast<int32_t>(yxaddr); m_ycAddr= static_cast<int32_t>(ycaddr); } int32_t m_yxAddr; int32_t m_ycAddr; void set_flg(int flg) { state_flg=flg; } int get_flg() { return state_flg; } void set_expect_time(int time) { expect_timedif=time; } float GetByteToFloat(BYTE data[4]) { FloatLongType value; value.ldata = data[0] | (data[1] << 8) | (data[2] << 16) | (data[3] << 24); return value.fdata; } QDateTime CP56TiToQDateTi(CP56Time time) { int MillSecond = (time.wMilliSeconds[1] << 8) + time.wMilliSeconds[0]; QTime sTime(time.byHours, time.byMinutes, MillSecond / 1000, MillSecond % 1000); QDate sDate(time.byYears + 2000, time.byMonths, time.byDays); return QDateTime(sDate, sTime); } signals: void data_fit(int flg,QString name); private: T m_data; };

优化这段代码 int Lcd_Modify_Param(int ikey,unsigned char mode,int _boardid,int gapid,int ioa,int digit) { float param; int len; int index = digit - 1; const float add_arr[3][8] = { {pow(10,0), 0 ,pow(10,-1),pow(10,-2), pow(10,-3),pow(10,-4)}, {pow(10,1),pow(10,0), 0 , pow(10,-1), pow(10,-2),pow(10,-3),pow(10,-4)}, {pow(10,2),pow(10,1),pow(10,0), 0 , pow(10,-1),pow(10,-2),pow(10,-3),pow(10,-4)} }; if(mode == ALTER_RUNPARAM) param = get_RunParaInfo_val(_boardid,gapid,ioa); else if (mode == ALTER_PROTECT) param = get_ActionDZInfo_val(_boardid,gapid,ioa); else if (mode == ALTER_SERI) param = gRunPara.COMMS_SerialInfo[gapid][ioa].val; if ((mode == ALTER_SERI) || (mode == ALTER_PROTECT&&(ioa == RT1064KZZ_UAB_CH || ioa == RT1064KZZ_UBC_CH || ioa == RT1064_DZ_CHZCS))) { printf("szName:%s\n",gRunPara.gap_ActionDZInfo[gapid][ioa].szName); param = SetInteger(ikey,param,digit); printf("param:%f\n", param); } else { len = snprintf(NULL, 0, "%0.3f", param); // 获取字符串长度 char buf[len+1]; // 创建缓冲区 snprintf(buf, len+1, "%0.3f", param); // 将浮点数转换为字符串 if (ikey == LCD_KEY_ADD) { if (len >= 5 && len <= 7 && index >= 0 && index <= 7) param += add_arr[len-5][index]; } else if(ikey == LCD_KEY_DECREASE) { if (len >= 5 && len <= 7 && index >= 0 && index <= 7) param -= add_arr[len-5][index]; } } if (param >= 0) { if(mode == ALTER_RUNPARAM) { if (_boardid == UNIT_PUBLIC_MX6) { if(gRunPara.ALLptRunParaInfo[ioa].IDbyBoard == 0) { if(gRunPara.ALLptRunParaInfo[ioa].IDbyPt < MX6RUN_TOTALSUM) { gRunPara.pub_RunParaInfo[gRunPara.ALLptRunParaInfo[ioa].IDbyPt].val= param; } } else { if (gRunPara.ALLptRunParaInfo[ioa].IDbyPt != RT1064KZZ_PTDX && gRunPara.ALLptRunParaInfo[ioa].IDbyPt < RUN_INNER_PARA_SIZE) { gRunPara.gap_RunParaInfo[1][gRunPara.ALLptRunParaInfo[ioa].IDbyPt].val= param; } else if ((gRunPara.ALLptRunParaInfo[ioa].IDbyPt == RT1064KZZ_PTDX || gRunPara.ALLptRunParaInfo[ioa].IDbyPt >= RT1064_DZ_YY) && gRunPara.ALLptRunParaInfo[ioa].IDbyPt < RT1064_YS_TOTALSUM) //--四个参数在 内部动作参数区 { gRunPara.gap_ActionDZInfo[1][gRunPara.ALLptRunParaInfo[ioa].IDbyPt].val= param; } } } else if (_boardid == UNIT_GAP_RT1064) gRunPara.gap_RunParaInfo[gapid][ioa].val= param; } else if (mode == ALTER_PROTECT) { if (_boardid == UNIT_PUBLIC_MX6) gRunPara.pub_ActionDZInfo[ioa].val = param; else { if (param <= 999999) gRunPara.gap_ActionDZInfo[gapid][ioa].val = param; } } else if (mode == ALTER_SERI) { if (param <= 999999) gRunPara.COMMS_SerialInfo[gapid][ioa].val = param; } } return 1; }

namespace SandwichCalories { class Program { static void Main(string[] args) { // sandwich ingredients and their associated calories Dictionary<string, int> ingredients = new Dictionary<string, int>() { { "Bread", 100 }, { "Ham", 150 }, { "Lettuce", 10 }, { "Tomato", 20 }, { "Mayonnaise", 50 }, { "Cheese", 120 } }; // prompt user for calorie range Console.Write("Enter minimum calories: "); int min_calories = int.Parse(Console.ReadLine()); Console.Write("Enter maximum calories: "); int max_calories = int.Parse(Console.ReadLine()); // calculate the minimum and maximum calories for the sandwich int min_sandwich_calories = 2 * ingredients["Bread"] + ingredients.Values.Min() * 2; int max_sandwich_calories = 2 * ingredients["Bread"] + ingredients.Values.Max() * 2; // check if the calorie range is valid if (max_calories < min_sandwich_calories) { Console.WriteLine("Sorry, it is impossible to create a sandwich within the given calorie range."); } else { // create the sandwich List<string> sandwich = new List<string> { "Bread", "Bread" }; int sandwich_calories = 2 * ingredients["Bread"]; while (sandwich_calories < min_calories) { // add random ingredient string ingredient = ingredients.Keys.ElementAt(new Random().Next(ingredients.Count)); sandwich.Add(ingredient); sandwich_calories += ingredients[ingredient]; } while (sandwich_calories <= max_calories) { // add random ingredient string ingredient = ingredients.Keys.ElementAt(new Random().Next(ingredients.Count)); // check if the ingredient is the same as the previous one if (sandwich.Count >= 3 && ingredient == sandwich[sandwich.Count - 2]) { continue; } sandwich.Add(ingredient); sandwich_calories += ingredients[ingredient]; // check if the sandwich is already at the maximum calorie limit if (sandwich_calories == max_sandwich_calories) { break; } } // add the last slice of bread sandwich.Add("Bread"); // print the sandwich and its total calories Console.WriteLine("Your sandwich: " + string.Join(", ", sandwich)); Console.WriteLine("Total calories: " + sandwich_calories); } } } } 改进代码

对下面这段C++代码进行优化#include<iostream> #include<vector> using namespace std; class Packet { }; class MAC { private: int address; vector buffer; bool transmitting; int transmit_time; int backoff_time; public: MAC(int address) { this->address = address; this->transmitting = false; this->transmit_time = 0; this->backoff_time = 0; } bool gettransmitting() { return &transmitting; } int * gettransmit_time() { return &transmit_time; } int getbackoff_time() { return &backoff_time; } int* getaddress() { return &address; } void transmit(Packet packet) { if (transmitting) { buffer.push_back(packet); } else { transmitting = true; transmit_time = 10; send_packet(packet); } } void send_packet(Packet packet) { // 发送数据包 transmit_time -= 1; if (transmit_time == 0) { transmitting = false; check_buffer(); } } void check_buffer() { if (buffer.size() > 0) { Packet packet = buffer.front(); buffer.erase(buffer.begin()); transmit(packet); } else { backoff_time = 10; } } void handle_backoff() { if (backoff_time > 0) { backoff_time -= 1; } else { check_buffer(); } } }; class SMAC { private: vector<MAC> nodes; int time; public: SMAC(vector<MAC> nodes) { this->nodes = nodes; this->time = 0; } void run() { while (true) { time += 1; for (int i = 0; i < nodes.size(); i++) { MAC node = nodes[i]; if (node.gettransmitting()) { node.send_packet(Packet()); } else if (node.getbackoff_time() > 0) { node.handle_backoff(); } else { // 随机发送数据包 if (rand() % 100 < 10) { Packet packet(node.getaddress(), nodes[rand() % nodes.size()].getaddress()); node.transmit(packet); } } } } } }; int main() { return 0; }

请给一下代码加注释,越详细越好。AStar.h:#ifndef ASTAR_H #define ASTAR_H #include <vector> using namespace std; class AStar { public: AStar(int n); void add_edge(int u, int v, int w); void set_heuristic(vector<int>& h); void shortest_path(int s, int t); vector<int> get_dist(); vector<int> get_prev(); private: struct edge { int to, weight; edge(int t, int w) : to(t), weight(w) {} }; int n; vector<vector<edge>> graph; vector<vector<edge>> rev_graph; vector<int> dist; vector<int> prev; vector<int> heuristic; }; class Astar { }; #endif;AStar.cpp:#include "AStar.h" #include <vector> #include <queue> #include using namespace std; AStar::AStar(int n) : n(n), graph(n), rev_graph(n), dist(n, numeric_limits<int>::max()), prev(n, -1), heuristic(n, 0) {} void AStar::add_edge(int u, int v, int w) { graph[u].push_back(edge(v, w)); rev_graph[v].push_back(edge(u, w)); } void AStar::set_heuristic(vector<int>& h) { heuristic = h; } void AStar::shortest_path(int s, int t) { priority_queue, vector>, greater>> pq; dist[s] = 0; pq.push(make_pair(heuristic[s], s)); while (!pq.empty()) { int u = pq.top().second; pq.pop(); if (u == t) return; for (auto& e : graph[u]) { int v = e.to; int w = e.weight; if (dist[v] > dist[u] + w) { dist[v] = dist[u] + w; prev[v] = u; pq.push(make_pair(dist[v] + heuristic[v], v)); } } for (auto& e : rev_graph[u]) { int v = e.to; int w = e.weight; if (dist[v] > dist[u] + w) { dist[v] = dist[u] + w; prev[v] = u; pq.push(make_pair(dist[v] + heuristic[v], v)); } } } } vector<int> AStar::get_dist() { return dist; } vector<int> AStar::get_prev() { return prev; }

最新推荐

recommend-type

计算机基础知识试题与解答

"计算机基础知识试题及答案-(1).doc" 这篇文档包含了计算机基础知识的多项选择题,涵盖了计算机历史、操作系统、计算机分类、电子器件、计算机系统组成、软件类型、计算机语言、运算速度度量单位、数据存储单位、进制转换以及输入/输出设备等多个方面。 1. 世界上第一台电子数字计算机名为ENIAC(电子数字积分计算器),这是计算机发展史上的一个重要里程碑。 2. 操作系统的作用是控制和管理系统资源的使用,它负责管理计算机硬件和软件资源,提供用户界面,使用户能够高效地使用计算机。 3. 个人计算机(PC)属于微型计算机类别,适合个人使用,具有较高的性价比和灵活性。 4. 当前制造计算机普遍采用的电子器件是超大规模集成电路(VLSI),这使得计算机的处理能力和集成度大大提高。 5. 完整的计算机系统由硬件系统和软件系统两部分组成,硬件包括计算机硬件设备,软件则包括系统软件和应用软件。 6. 计算机软件不仅指计算机程序,还包括相关的文档、数据和程序设计语言。 7. 软件系统通常分为系统软件和应用软件,系统软件如操作系统,应用软件则是用户用于特定任务的软件。 8. 机器语言是计算机可以直接执行的语言,不需要编译,因为它直接对应于硬件指令集。 9. 微机的性能主要由CPU决定,CPU的性能指标包括时钟频率、架构、核心数量等。 10. 运算器是计算机中的一个重要组成部分,主要负责进行算术和逻辑运算。 11. MIPS(Millions of Instructions Per Second)是衡量计算机每秒执行指令数的单位,用于描述计算机的运算速度。 12. 计算机存储数据的最小单位是位(比特,bit),是二进制的基本单位。 13. 一个字节由8个二进制位组成,是计算机中表示基本信息的最小单位。 14. 1MB(兆字节)等于1,048,576字节,这是常见的内存和存储容量单位。 15. 八进制数的范围是0-7,因此317是一个可能的八进制数。 16. 与十进制36.875等值的二进制数是100100.111,其中整数部分36转换为二进制为100100,小数部分0.875转换为二进制为0.111。 17. 逻辑运算中,0+1应该等于1,但选项C错误地给出了0+1=0。 18. 磁盘是一种外存储设备,用于长期存储大量数据,既可读也可写。 这些题目旨在帮助学习者巩固和检验计算机基础知识的理解,涵盖的领域广泛,对于初学者或需要复习基础知识的人来说很有价值。
recommend-type

管理建模和仿真的文件

管理Boualem Benatallah引用此版本:布阿利姆·贝纳塔拉。管理建模和仿真。约瑟夫-傅立叶大学-格勒诺布尔第一大学,1996年。法语。NNT:电话:00345357HAL ID:电话:00345357https://theses.hal.science/tel-003453572008年12月9日提交HAL是一个多学科的开放存取档案馆,用于存放和传播科学研究论文,无论它们是否被公开。论文可以来自法国或国外的教学和研究机构,也可以来自公共或私人研究中心。L’archive ouverte pluridisciplinaire
recommend-type

【进阶】音频处理基础:使用Librosa

![【进阶】音频处理基础:使用Librosa](https://picx.zhimg.com/80/v2-a39e5c9bff1d920097341591ca8a2dfe_1440w.webp?source=1def8aca) # 2.1 Librosa库的安装和导入 Librosa库是一个用于音频处理的Python库。要安装Librosa库,请在命令行中输入以下命令: ``` pip install librosa ``` 安装完成后,可以通过以下方式导入Librosa库: ```python import librosa ``` 导入Librosa库后,就可以使用其提供的各种函数
recommend-type

设置ansible 开机自启

Ansible是一个强大的自动化运维工具,它可以用来配置和管理服务器。如果你想要在服务器启动时自动运行Ansible任务,通常会涉及到配置服务或守护进程。以下是使用Ansible设置开机自启的基本步骤: 1. **在主机上安装必要的软件**: 首先确保目标服务器上已经安装了Ansible和SSH(因为Ansible通常是通过SSH执行操作的)。如果需要,可以通过包管理器如apt、yum或zypper安装它们。 2. **编写Ansible playbook**: 创建一个YAML格式的playbook,其中包含`service`模块来管理服务。例如,你可以创建一个名为`setu
recommend-type

计算机基础知识试题与解析

"计算机基础知识试题及答案(二).doc" 这篇文档包含了计算机基础知识的多项选择题,涵盖了操作系统、硬件、数据表示、存储器、程序、病毒、计算机分类、语言等多个方面的知识。 1. 计算机系统由硬件系统和软件系统两部分组成,选项C正确。硬件包括计算机及其外部设备,而软件包括系统软件和应用软件。 2. 十六进制1000转换为十进制是4096,因此选项A正确。十六进制的1000相当于1*16^3 = 4096。 3. ENTER键是回车换行键,用于确认输入或换行,选项B正确。 4. DRAM(Dynamic Random Access Memory)是动态随机存取存储器,选项B正确,它需要周期性刷新来保持数据。 5. Bit是二进制位的简称,是计算机中数据的最小单位,选项A正确。 6. 汉字国标码GB2312-80规定每个汉字用两个字节表示,选项B正确。 7. 微机系统的开机顺序通常是先打开外部设备(如显示器、打印机等),再开启主机,选项D正确。 8. 使用高级语言编写的程序称为源程序,需要经过编译或解释才能执行,选项A正确。 9. 微机病毒是指人为设计的、具有破坏性的小程序,通常通过网络传播,选项D正确。 10. 运算器、控制器及内存的总称是CPU(Central Processing Unit),选项A正确。 11. U盘作为外存储器,断电后存储的信息不会丢失,选项A正确。 12. 财务管理软件属于应用软件,是为特定应用而开发的,选项D正确。 13. 计算机网络的最大好处是实现资源共享,选项C正确。 14. 个人计算机属于微机,选项D正确。 15. 微机唯一能直接识别和处理的语言是机器语言,它是计算机硬件可以直接执行的指令集,选项D正确。 16. 断电会丢失原存信息的存储器是半导体RAM(Random Access Memory),选项A正确。 17. 硬盘连同驱动器是一种外存储器,用于长期存储大量数据,选项B正确。 18. 在内存中,每个基本单位的唯一序号称为地址,选项B正确。 以上是对文档部分内容的详细解释,这些知识对于理解和操作计算机系统至关重要。
recommend-type

"互动学习:行动中的多样性与论文攻读经历"

多样性她- 事实上SCI NCES你的时间表ECOLEDO C Tora SC和NCESPOUR l’Ingén学习互动,互动学习以行动为中心的强化学习学会互动,互动学习,以行动为中心的强化学习计算机科学博士论文于2021年9月28日在Villeneuve d'Asq公开支持马修·瑟林评审团主席法布里斯·勒菲弗尔阿维尼翁大学教授论文指导奥利维尔·皮耶昆谷歌研究教授:智囊团论文联合主任菲利普·普雷教授,大学。里尔/CRISTAL/因里亚报告员奥利维耶·西格德索邦大学报告员卢多维奇·德诺耶教授,Facebook /索邦大学审查员越南圣迈IMT Atlantic高级讲师邀请弗洛里安·斯特鲁布博士,Deepmind对于那些及时看到自己错误的人...3谢谢你首先,我要感谢我的两位博士生导师Olivier和Philippe。奥利维尔,"站在巨人的肩膀上"这句话对你来说完全有意义了。从科学上讲,你知道在这篇论文的(许多)错误中,你是我可以依
recommend-type

【基础】网络编程入门:使用HTTP协议

![【基础】网络编程入门:使用HTTP协议](https://img-blog.csdnimg.cn/direct/4fbc6b5a6d744a519429654f56ea988e.png) # 1. 网络编程基础** **1.1 网络基础知识** 网络是连接计算机和设备的系统,允许它们交换数据和资源。它由节点(计算机、服务器、路由器等)和连接它们的数据链路组成。网络可以是局域网(LAN)、广域网(WAN)或互联网。 **1.2 TCP/IP协议栈** TCP/IP协议栈是一组通信协议,用于在网络上传输数据。它分为四层: * **链路层:**处理物理连接和数据传输。 * **网络层:
recommend-type

时间序列大模型的研究进展

时间序列大模型是近年来自然语言处理领域的一个热门研究方向,它们专注于理解和生成基于时间顺序的数据,比如文本序列、音频或视频信号。这类模型通常结合了Transformer架构(如BERT、GPT等)与循环神经网络(RNNs, LSTM)的长短期记忆能力,以捕捉序列数据中的时间依赖性。 近期的研究进展包括: 1. 长序列建模:研究人员一直在努力提高模型能够处理长序列的能力,例如M6和Turing-NLG,这些模型扩展了序列长度限制,增强了对长期依赖的理解。 2. 结合外部知识:一些模型开始融合外部知识库,如ProphetNet和D-PTM,以提升对复杂时间序列的预测精度。 3. 强化学习和
recommend-type

计算机基础知识试题与解析

"这份文档是计算机基础知识的试题集,包含了多项选择题,涵盖了计算机系统的构成、键盘功能、数据单位、汉字编码、开机顺序、程序类型、计算机病毒、内存分类、计算机网络的应用、计算机类型、可执行语言、存储器角色、软件类别、操作系统归属、存储容量单位、网络类型以及微机发展的标志等多个知识点。" 1. 计算机系统由硬件系统和软件系统组成,A选项仅提及计算机及外部设备,B选项提到了一些外部设备但不完整,C选项正确,D选项将硬件和软件混淆为系统硬件和系统软件。 2. ENTER键在计算机中是回车换行键,用于确认输入或换行,B选项正确。 3. Bit是二进制位的简称,是计算机中最基本的数据单位,A选项正确;字节Byte是8个Bit组成的单位,C选项的字节是正确的,但题目中问的是Bit。 4. 汉字国标码GB2312-80规定,每个汉字用两个字节表示,B选项正确。 5. 微机系统的开机顺序通常是先开启外部设备(如显示器、打印机等),最后开启主机,D选项符合这一顺序。 6. 使用高级语言编写的程序称为源程序,需要经过编译或解释才能运行,A选项正确。 7. 微机病毒是指特制的、具有破坏性的小程序,可以影响计算机的正常运行,D选项正确。 8. 微型计算机的运算器、控制器及内存的总称是CPU,A选项错误,应是C选项的主机。 9. 软磁盘(软盘)中的信息在断电后不会丢失,因为它是非易失性存储,A选项正确。 10. 计算机网络的最大好处是实现资源共享,C选项正确。 11. 个人计算机通常指的是微机,D选项正确。 12. 微机唯一能直接识别和处理的语言是机器语言,D选项正确。 13. 计算机存储器是记忆部件,用于存储数据和指令,D选项正确。 14. 人事档案管理程序属于应用软件,专门用于特定用途,B选项正确。 15. DOS在计算机中属于系统软件,负责管理和控制计算机硬件和软件资源,C选项正确。 16. 反映计算机存储容量的基本单位是字节,B选项正确。 17. LAN网指的是局域网,A选项正确。 18. 微型计算机的发展主要以微处理器的发展为特征,C选项正确。 以上是对试题中涉及的计算机基础知识的详细解析。这些知识点构成了计算机科学的基础,并且对于理解和操作计算机系统至关重要。
recommend-type

关系数据表示学习

关系数据卢多维奇·多斯桑托斯引用此版本:卢多维奇·多斯桑托斯。关系数据的表示学习机器学习[cs.LG]。皮埃尔和玛丽·居里大学-巴黎第六大学,2017年。英语。NNT:2017PA066480。电话:01803188HAL ID:电话:01803188https://theses.hal.science/tel-01803188提交日期:2018年HAL是一个多学科的开放存取档案馆,用于存放和传播科学研究论文,无论它们是否被公开。论文可以来自法国或国外的教学和研究机构,也可以来自公共或私人研究中心。L’archive ouverte pluridisciplinaireUNIVERSITY PIERRE和 MARIE CURIE计算机科学、电信和电子学博士学院(巴黎)巴黎6号计算机科学实验室D八角形T HESIS关系数据表示学习作者:Ludovic DOS SAntos主管:Patrick GALLINARI联合主管:本杰明·P·伊沃瓦斯基为满足计算机科学博士学位的要求而提交的论文评审团成员:先生蒂埃里·A·退休记者先生尤尼斯·B·恩