教学课程资源库 更多>>

关键词： 新工科   计算机科学与技术   地方本科院校   实践教学   校企合作  

摘要： 为满足新工科建设背景下新行业对工程专业人才的需求,文章分别从新工科的专题研讨、实践教学体系、校企合作与多学科交叉等方面分析专业改造升级过程中所面临的主要问题,并提出相关的解决方案,对目前传统的计算机科学与技术专业加以优化升级,对培养新工科背景下解决实际复杂工程问题需求的专业人才的途径进行探索。

摘要： Mr. Heckman will provide a lecture and Q&A session on cutting edge advances in computer science and their cumulative potential for good and abuse in society. The core discuss will circle around the topics of Artificial Intelligence, Super Computers, Quantum Computing, RFI chips, Digital Currencies, Global WiFi and Brain-computer *** goal is to look at the conjunction of these rapidly advancing technologies and challenge the computer engineering students and professionals to envision the amazing opportunities these technologies can provide while drawing attention to the possible hazards to society.

摘要： The effectiveness of individualization of teaching computer science to students of a technical university based on adaptive management technology is determined by the implementation of the following principles: visibility; propaedeutic conditionality of studying computer science; contextuality of learning in a broad and narrow sense; individualization of learning; independence; informativeness; orientation of the learning process to the development of personality, taking into account its individual characteristics; flexibility and variability of the organization of training; the presence and consideration of semantic connections within the educational material; the formation of the student's subjective position; the relationship of arbitrariness and self-regulation; positive perspectives and self-management; self- development and self-realization, and will contribute to the creation of a methodological system for teaching computer science, focused on the formation of skills to carry out educational activities in the field of independent solution of professionally directed tasks.

关键词： Training   Backpropagation   Deep learning   Computer science   Scalability   Estimation   Tutorials  

摘要： This tutorial paper surveys provably optimal alternatives to end-to-end backpropagation (E2EBP) - the de facto standard for training deep architectures. Modular training refers to strictly local training without both the forward and the backward pass, i.e., dividing a deep architecture into several nonoverlapping modules and training them separately without any end-to-end operation. Between the fully global E2EBP and the strictly local modular training, there are weakly modular hybrids performing training without the backward pass only. These alternatives can match or surpass the performance of E2EBP on challenging datasets such as ImageNet, and are gaining increasing attention primarily because they offer practical advantages over E2EBP, which will be enumerated herein. In particular, they allow for greater modularity and transparency in deep learning workflows, aligning deep learning with the mainstream computer science engineering that heavily exploits modularization for scalability. Modular training has also revealed novel insights about learning and has further implications on other important research domains. Specifically, it induces natural and effective solutions to some important practical problems such as data efficiency and transferability estimation.

摘要： As computer science grows in popularity, more faculty are needed to staff computer science courses. Approval for full-time tenure-track faculty and permanent instructor positions can lag student enrollment demands. One common strategy to meet student enrollment needs is to expand sections sizes. Another strategy is to staff courses with adjunct faculty. This paper describes the experiences of alumni serving as adjunct faculty members to teach introductory computer science labs. These alumni learned introductory programming by completing these labs as students, and then served as role models for computer science majors by providing professional and career advice. The paper provides an overview of the introductory computing labs, "professions" talks the alumni gave each week, and perspectives from the alumni after teaching the labs.

关键词： 计算机科学   教学体系设计   双导师  

摘要： 阐述计算机科学与技术课程的教学体系的设计,可行方式,包括教学的目的性、科学严谨的体系、保证体系的建立、双导师制度、考核制度、合理安排课程内容。

关键词： Quantization (signal)   Distributed databases   Field programmable gate arrays   Degradation   Computer science   Open area test sites   Hardware   DNN quantization   significant bits   fitting distribution   cheap projection   distribution aligner   FPGA accelerator  

摘要： Quantization has been proven to be a vital method for improving the inference efficiency of deep neural networks (DNNs). However, it is still challenging to strike a good balance between accuracy and efficiency while quantizing DNN weights or activation values from high-precision formats to their quantized counterparts. We propose a new method called elastic significant bit quantization (ESB) that controls the number of significant bits of quantized values to obtain better inference accuracy with fewer resources. We design a unified mathematical formula to constrain the quantized values of the ESB with a flexible number of significant bits. We also introduce a distribution difference aligner (DDA) to quantitatively align the distributions between the full-precision weight or activation values and quantized values. Consequently, ESB is suitable for various bell-shaped distributions of weights and activation of DNNs, thus maintaining a high inference accuracy. Benefitting from fewer significant bits of quantized values, ESB can reduce the multiplication complexity. We implement ESB as an accelerator and quantitatively evaluate its efficiency on FPGAs. Extensive experimental results illustrate that ESB quantization consistently outperforms state-of-the-art methods and achieves average accuracy improvements of 4.78%, 1.92%, and 3.56% over AlexNet, ResNet18, and MobileNetV2, respectively. Furthermore, ESB as an accelerator can achieve 10.95 GOPS peak performance of 1k LUTs without DSPs on the Xilinx ZCU102 FPGA platform. Compared with CPU, GPU, and state-of-the-art accelerators on FPGAs, the ESB accelerator can improve the energy efficiency by up to 65x, 11x, and 26x, respectively.

摘要： In this paper we describe techniques intentionally designed to promote inclusivity and equity in an introduction to computer science course. We describe approaches for using randomly-drawn name cards as an alternative to cold-calling students for participation in class. We also discuss using an online polling technique that utilizes components of the Peer Instruction pedagogy to solicit low-stakes individual contributions. In each case, we motivate the "best practices" we have experienced and propose methods for making computer science classrooms more inclusive and equitable.

摘要： The COVID-19 pandemic provided motivation to shift course modalities and assignments to online experiences as many universities suddenly required all course instruction to move online. In response to the continuing global health crisis, many universities offered the majority of their courses with online modality for over twelve months following the beginning of the pandemic. In addition to classroom changes, students and faculty faced health, economic, and social stresses not previously experienced. We compare survey data of student perceptions of course experiences during their online experiences and after returning to a traditional in-person course environment. We identify student perceptions of tools that contributed to their success during online courses as well as challenges faced. Our survey data provides a window into how students felt during the online course experience and after returning to in-person classes during this unique period.

摘要： This paper presents a course model for changing the mindset of students as future leaders in technology-based fields. Research shows that entrepreneurial education within engineering is an important facet of degree programs; however there are not as many models incorporating this mindset focus into computer science education. The authors describe a "Business and Technology Ventures" course that is required for computer science majors. The topics, outline, and projects are described with potential adaptions so that others can adopt or adapt components of this course model. One of the specific benefits of this approach is that it increases job readiness by enhancing non-technical skills. This course has been offered three times, and the instructors are satisfied with students' achievement of the learning objectives and students' achievements.