34. (判断题, 2分) 1.1 Considering the bursty data transferring, a circuit switching network outperforms a packet switching network. • A. 对 • B. 错 35. (判断题, 2分) 1.2 There is no network congestion in a circuit switching network. • A. 对 • B. 错 36. (判断题, 2分) 1.3 Consider an application that transmits data at a steady rate, and once this application starts, it will stay on for a relatively long period of time. According to the characteristic, a packet-switched network would be more appropriate for this application than a circuit-switched network. • A. 对 • B. 错

时间: 2024-04-05 10:33:49 浏览: 164
PPTX

Considering a Trustworthy AI Governance Framework.pptx

34. (判断题, 2分) 1.1 错 (Packet switching networks are better suited for bursty data transferring.) 35. (判断题, 2分) 1.2 错 (Network congestion can occur in a circuit switching network.) 36. (判断题, 2分) 1.3 错 (A circuit-switched network would be more appropriate for an application that transmits data at a steady rate for a long period of time.)
阅读全文

相关推荐

用中文翻译:A coupled three-dimensional model is developed to study the internal parameter distributions of the MBPP fuel cell stack, considering fluid dynamics, electro-chemical reactions, multi-species mass transfer, twophase flow of water and thermal dynamics. The model geometry domains include anode MBPP, anode gas wavy flow field (5 parallel flow channels), anode GDL, anode catalyst layer (CL), membrane, cathode CL, cathode GDL, cathode gas wavy flow field (5 parallel flow channels), cathode MBPP and the two-layered coolant wavy flow fields at anode/cathode sides. According to the stack design, the design parameters of wavy flow fields for anode and cathode sides are the same but the phase deviation between their wave cycles presents 180◦. The two wavy flow fields of coolant, at the respective back sides of the anode and cathode plates, form the intercrossed two-layered coolant flow fields inside the MBPP, due to the phase difference of 180◦ between the wave cycles (Fig. 3). The mismatched flow field patterns between the neighbored fluid flows lead to complicated geometry and mesh building. The presented model geometry is divided into several layers (xz plane) according to the different domain materials so that the thin metallic plate and fluid domains with complicated 3D morphologies could be finely meshed layer by layer. As the real geometry of the experimental stack is too large for calculation, the modeled flow field consists of 5 parallel wavy channels, each of which includes 2 wave periods and corresponding inlet/outlet portions as well. To study the detailed thermal behavior of the presented design, the two-layered coolant fluid flow at the back side of the anode plate is considered and so is for the cathode plate. The counter flow operation is conducted where the air flows at the same direction with coolant but the opposite with hydrogen, shown in Fig. 3 (b).

3)A digital clock consists of a screen to display the time and a dial for setting in turn the year, month, day, hour and minute. Twisting the dial to the left reduces by one the value being changed but twisting it to the right increases it by one. Pushing the dial alters which value is being adjusted. At first, it is the year but after the dial is pushed once, it is the month, then after the dial is pushed again, it is the day and so on. Imagine the clock is represented by a class with attributes year, month, day etc. The following is what the code for a method rotateDialLeft() might look like. public void rotateDialLeft() { if (mode == YEAR_MODE) { year--; } else if (mode == MONTH_MODE) { month--; } else if (mode == DAY_MODE) { day--; } else if (mode == HOUR_MODE) { hour--; } else if (mode == MINUTE_MODE) { minute--; } } The code for rotateDialRight() is similar. Apply the Open-Closed Principle to explain why the above code is unsatisfactory from the design viewpoint, considering the possibility of future change to the code, giving an example of such a change. 5)Give the code required for the classes introduced in question 3), focusing on the code for a method selectState() which changes the value that is being adjusted from years to months. Make it clear in which classes the code is to be found. Assume the existence of other methods that are needed such as getMonthSetUpState(). 8)Suppose that in a multiplayer role-playing game, a class Client has a dependency to an interface Fighter with public methods attack(), defend() and escape(). The game designer now wishes for Client to use a class Wizard with three different but equivalent public methods castDestructionSpell(), shield() and portal(). Explain how it is possible to do this using an appropriate design pattern.

Algorithm 1: The online LyDROO algorithm for solving (P1). input : Parameters V , {γi, ci}Ni=1, K, training interval δT , Mt update interval δM ; output: Control actions 􏰕xt,yt􏰖Kt=1; 1 Initialize the DNN with random parameters θ1 and empty replay memory, M1 ← 2N; 2 Empty initial data queue Qi(1) = 0 and energy queue Yi(1) = 0, for i = 1,··· ,N; 3 fort=1,2,...,Kdo 4 Observe the input ξt = 􏰕ht, Qi(t), Yi(t)􏰖Ni=1 and update Mt using (8) if mod (t, δM ) = 0; 5 Generate a relaxed offloading action xˆt = Πθt 􏰅ξt􏰆 with the DNN; 6 Quantize xˆt into Mt binary actions 􏰕xti|i = 1, · · · , Mt􏰖 using the NOP method; 7 Compute G􏰅xti,ξt􏰆 by optimizing resource allocation yit in (P2) for each xti; 8 Select the best solution xt = arg max G 􏰅xti , ξt 􏰆 and execute the joint action 􏰅xt , yt 􏰆; { x ti } 9 Update the replay memory by adding (ξt,xt); 10 if mod (t, δT ) = 0 then 11 Uniformly sample a batch of data set {(ξτ , xτ ) | τ ∈ St } from the memory; 12 Train the DNN with {(ξτ , xτ ) | τ ∈ St} and update θt using the Adam algorithm; 13 end 14 t ← t + 1; 15 Update {Qi(t),Yi(t)}N based on 􏰅xt−1,yt−1􏰆 and data arrival observation 􏰙At−1􏰚N using (5) and (7). i=1 i i=1 16 end With the above actor-critic-update loop, the DNN consistently learns from the best and most recent state-action pairs, leading to a better policy πθt that gradually approximates the optimal mapping to solve (P3). We summarize the pseudo-code of LyDROO in Algorithm 1, where the major computational complexity is in line 7 that computes G􏰅xti,ξt􏰆 by solving the optimal resource allocation problems. This in fact indicates that the proposed LyDROO algorithm can be extended to solve (P1) when considering a general non-decreasing concave utility U (rit) in the objective, because the per-frame resource allocation problem to compute G􏰅xti,ξt􏰆 is a convex problem that can be efficiently solved, where the detailed analysis is omitted. In the next subsection, we propose a low-complexity algorithm to obtain G 􏰅xti, ξt􏰆. B. Low-complexity Algorithm for Optimal Resource Allocation Given the value of xt in (P2), we denote the index set of users with xti = 1 as Mt1, and the complementary user set as Mt0. For simplicity of exposition, we drop the superscript t and express the optimal resource allocation problem that computes G 􏰅xt, ξt􏰆 as following (P4) : maximize 􏰀j∈M0 􏰕ajfj/φ − Yj(t)κfj3􏰖 + 􏰀i∈M1 {airi,O − Yi(t)ei,O} (28a) τ,f,eO,rO 17 ,建立了什么模型

最新推荐

recommend-type

Trajectory modification considering dynamic constraints of autonomous robots.pdf

《考虑动态约束的自主机器人轨迹修改》 在自动驾驶领域,路径规划是至关重要的,它确保机器人或无人车辆能够安全、高效地从起点到达终点。传统的“弹性带”方法通过拉伸和压缩路径来避免障碍物,同时追求最短路径,...
recommend-type

大学英语四级写作模板库.pdf

Considering all these, while embracing the growth in science and technology, we should not neglect the value of a well-rounded education. 问题解决型作文模板则着重于提出问题并探讨解决方案。例如: ...
recommend-type

恋练有词纯单词顺序Unit1-Unit30.docx

"as a matter of fact"事实上,"substance"是实质,"stuff"是材料,"material"是材料,"fund"是基金,"fundamental"是基本的,"fundamentally"从根本上,"in the sector of"在...领域,"account for"解释或占比,...
recommend-type

JHU荣誉单变量微积分课程教案介绍

资源摘要信息:"jhu2017-18-honors-single-variable-calculus" 知识点一:荣誉单变量微积分课程介绍 本课程为JHU(约翰霍普金斯大学)的荣誉单变量微积分课程,主要针对在2018年秋季和2019年秋季两个学期开设。课程内容涵盖两个学期的微积分知识,包括整合和微分两大部分。该课程采用IBL(Inquiry-Based Learning)格式进行教学,即学生先自行解决问题,然后在学习过程中逐步掌握相关理论知识。 知识点二:IBL教学法 IBL教学法,即问题导向的学习方法,是一种以学生为中心的教学模式。在这种模式下,学生在教师的引导下,通过提出问题、解决问题来获取知识,从而培养学生的自主学习能力和问题解决能力。IBL教学法强调学生的主动参与和探索,教师的角色更多的是引导者和协助者。 知识点三:课程难度及学习方法 课程的第一次迭代主要包含问题,难度较大,学生需要有一定的数学基础和自学能力。第二次迭代则在第一次的基础上增加了更多的理论和解释,难度相对降低,更适合学生理解和学习。这种设计旨在帮助学生从实际问题出发,逐步深入理解微积分理论,提高学习效率。 知识点四:课程先决条件及学习建议 课程的先决条件为预演算,即在进入课程之前需要掌握一定的演算知识和技能。建议在使用这些笔记之前,先完成一些基础演算的入门课程,并进行一些数学证明的练习。这样可以更好地理解和掌握课程内容,提高学习效果。 知识点五:TeX格式文件 标签"TeX"意味着该课程的资料是以TeX格式保存和发布的。TeX是一种基于排版语言的格式,广泛应用于学术出版物的排版,特别是在数学、物理学和计算机科学领域。TeX格式的文件可以确保文档内容的准确性和排版的美观性,适合用于编写和分享复杂的科学和技术文档。
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

【实战篇:自定义损失函数】:构建独特损失函数解决特定问题,优化模型性能

![损失函数](https://img-blog.csdnimg.cn/direct/a83762ba6eb248f69091b5154ddf78ca.png) # 1. 损失函数的基本概念与作用 ## 1.1 损失函数定义 损失函数是机器学习中的核心概念,用于衡量模型预测值与实际值之间的差异。它是优化算法调整模型参数以最小化的目标函数。 ```math L(y, f(x)) = \sum_{i=1}^{N} L_i(y_i, f(x_i)) ``` 其中,`L`表示损失函数,`y`为实际值,`f(x)`为模型预测值,`N`为样本数量,`L_i`为第`i`个样本的损失。 ## 1.2 损
recommend-type

如何在ZYNQMP平台上配置TUSB1210 USB接口芯片以实现Host模式,并确保与Linux内核的兼容性?

要在ZYNQMP平台上实现TUSB1210 USB接口芯片的Host模式功能,并确保与Linux内核的兼容性,首先需要在硬件层面完成TUSB1210与ZYNQMP芯片的正确连接,保证USB2.0和USB3.0之间的硬件电路设计符合ZYNQMP的要求。 参考资源链接:[ZYNQMP USB主机模式实现与测试(TUSB1210)](https://wenku.csdn.net/doc/6nneek7zxw?spm=1055.2569.3001.10343) 具体步骤包括: 1. 在Vivado中设计硬件电路,配置USB接口相关的Bank502和Bank505引脚,同时确保USB时钟的正确配置。
recommend-type

Naruto爱好者必备CLI测试应用

资源摘要信息:"Are-you-a-Naruto-Fan:CLI测验应用程序,用于检查Naruto狂热者的知识" 该应用程序是一个基于命令行界面(CLI)的测验工具,设计用于测试用户对日本动漫《火影忍者》(Naruto)的知识水平。《火影忍者》是由岸本齐史创作的一部广受欢迎的漫画系列,后被改编成同名电视动画,并衍生出一系列相关的产品和文化现象。该动漫讲述了主角漩涡鸣人从忍者学校开始的成长故事,直到成为木叶隐村的领袖,期间包含了忍者文化、战斗、忍术、友情和忍者世界的政治斗争等元素。 这个测验应用程序的开发主要使用了JavaScript语言。JavaScript是一种广泛应用于前端开发的编程语言,它允许网页具有交互性,同时也可以在服务器端运行(如Node.js环境)。在这个CLI应用程序中,JavaScript被用来处理用户的输入,生成问题,并根据用户的回答来评估其对《火影忍者》的知识水平。 开发这样的测验应用程序可能涉及到以下知识点和技术: 1. **命令行界面(CLI)开发:** CLI应用程序是指用户通过命令行或终端与之交互的软件。在Web开发中,Node.js提供了一个运行JavaScript的环境,使得开发者可以使用JavaScript语言来创建服务器端应用程序和工具,包括CLI应用程序。CLI应用程序通常涉及到使用诸如 commander.js 或 yargs 等库来解析命令行参数和选项。 2. **JavaScript基础:** 开发CLI应用程序需要对JavaScript语言有扎实的理解,包括数据类型、函数、对象、数组、事件循环、异步编程等。 3. **知识库构建:** 测验应用程序的核心是其问题库,它包含了与《火影忍者》相关的各种问题。开发人员需要设计和构建这个知识库,并确保问题的多样性和覆盖面。 4. **逻辑和流程控制:** 在应用程序中,需要编写逻辑来控制测验的流程,比如问题的随机出现、计时器、计分机制以及结束时的反馈。 5. **用户界面(UI)交互:** 尽管是CLI,用户界面仍然重要。开发者需要确保用户体验流畅,这包括清晰的问题呈现、简洁的指令和友好的输出格式。 6. **模块化和封装:** 开发过程中应当遵循模块化原则,将不同的功能分隔开来,以便于管理和维护。例如,可以将问题生成器、计分器和用户输入处理器等封装成独立的模块。 7. **单元测试和调试:** 测验应用程序在发布前需要经过严格的测试和调试。使用如Mocha或Jest这样的JavaScript测试框架可以编写单元测试,并通过控制台输出调试信息来排除故障。 8. **部署和分发:** 最后,开发完成的应用程序需要被打包和分发。如果是基于Node.js的应用程序,常见的做法是将其打包为可执行文件(如使用electron或pkg工具),以便在不同的操作系统上运行。 根据提供的文件信息,虽然具体细节有限,但可以推测该应用程序可能采用了上述技术点。用户通过点击提供的链接,可能将被引导到一个网页或直接下载CLI应用程序的可执行文件,从而开始进行《火影忍者》的知识测验。通过这个测验,用户不仅能享受答题的乐趣,还可以加深对《火影忍者》的理解和认识。
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

【强化学习损失函数探索】:奖励函数与损失函数的深入联系及优化策略

![【强化学习损失函数探索】:奖励函数与损失函数的深入联系及优化策略](https://cdn.codeground.org/nsr/images/img/researchareas/ai-article4_02.png) # 1. 强化学习中的损失函数基础 强化学习(Reinforcement Learning, RL)是机器学习领域的一个重要分支,它通过与环境的互动来学习如何在特定任务中做出决策。在强化学习中,损失函数(loss function)起着至关重要的作用,它是学习算法优化的关键所在。损失函数能够衡量智能体(agent)的策略(policy)表现,帮助智能体通过减少损失来改进自