教学课程资源库 更多>>

关键词： Frequency modulation   Indexes   Machine learning   Tools   Computer science   Linguistics   XAI   explainable artificial intelligence   data fusion   information fusion   deep learning  

摘要： The modern era of machine learning is focused on data-driven solutions. While this has resulted in astonishing leaps in numerous applications, explainability has not witnessed the same growth. The reality is, most machine learning solutions are black boxes. Herein, we focus on data/information fusion in machine learning. Specifically, we explore four eXplainable Artificial Intelligence (XAI) questions relative to Choquet integral;(i) what is the quality of our inputs and their interactions, (ii) how is the information being combined, (iii) what is the quality of our training data (and thus our learned models), and (iv) what trust do we place in an output? Previously, we derived an initial set of indices for (i)-(iv) on the premise of perfect knowledge. Herein, we make XAI more accurate by taking into consideration what the machine learned. A combination of synthetic data and real-world experiments from remote sensing for fusing deep learners in the context of classification are explored. Our approach leads to performance gain, insights into what was learned, and it helps us realize better future solutions.

关键词： Education   Systematics   Proposals   Data mining   Terminology   Teamwork   Planning   Active learning   computer science   problem-based learning (PBL)   systematic mapping  

摘要： Contribution: This article adds to the results of previous systematic mapping study by addressing a more ample context of problem-based learning (PBL) in computing education. Background: PBL is defined as an instructional method of constructivist teaching that uses real problems as a motivating element for learning. Although PBL was born in medical education, it has been used in computing education to facilitate the students' engagement and learning capacity, contributing to developing skills, such as teamwork, holistic vision, critical thinking, and solving problem. Considering that approach much more descriptive than prescriptive, it favors the implementation of diverse methodologies on its behalf. Research Question: "How the PBL approach has been applied in teaching computing?" Methodology: From the initial set of 3837 studies, 102 primary studies were selected and categorized through Kitchenham methodology for analysis from 1999 to 2019. Findings: Based on these studies, it was possible to verify a greater adoption of PBL in undergraduate education and a great diversity of strategies involving real-world problems, developing technical and no-technical skills and making the student much more motivated and engaged. Challenges were also mapped, which shows a very interesting field for new research.

关键词： Semantics   Training   Manifolds   Training data   Bridges   Computer science   Correlation   Cross-modal hashing   imbalanced multi-modal data   adversarial tri-fusion hashing   manifold structure  

摘要： Cross-modal retrieval has received increasing attentions for efficient retrieval across different modalities, and hashing technique has made significant progress recently due to its low storage cost and high query speed. However, most existing cross-modal hashing works still face the challenges of narrowing down the semantic gap between different modalities and training with imbalanced multi-modal data. This article presents an efficient Adversarial Tri-Fusion Hashing Network (ATFH-N) for cross-modal retrieval, which lies among the early attempts to incorporate adversarial learning for working with imbalanced multi-modal data. Specifically, a triple fusion network associated with zero padding operation is proposed to adapt either balanced or imbalanced multi-modal training data. At the same time, an adversarial training mechanism is leveraged to maximally bridge the semantic gap of the common representations between balanced and imbalanced data. Further, a label prediction network is utilized to guide the feature learning process and promote hash code learning, while additionally embedding the manifold structure to preserve both inter-modal and intra-modal similarities. Through the joint exploitation of the above, the underlying semantic structure of multimedia data can be well preserved in Hamming space, which can benefit various cross-modal retrieval tasks. Extensive experiments on three benchmark datasets show that the proposed ATFH-N method yields the comparable performance in balanced scenario and brings substantial improvements over the state-of-the-art methods in imbalanced scenarios.

摘要： Media headings about the mental health of the adolescent population during the COVID-19 pandemic have projected serious short-term and longer-term consequences of the pandemic and the measures taken to limit the spread of the virus. Headlines sugg...

关键词： Education   Engineering profession   Psychology   Task analysis   Instruments   Computer science   Encoding   Computer science (CS)   motivation   self-regulated learning (SRL)   undergraduate  

摘要： Contribution: This article presents a synthesis of the findings and implications from the IC2Think program of research in undergraduate computer science (CS) courses examining student motivation and self-regulated learning (SRL). These studies illuminate both the difficulty and potential for motivating CS students, as well as the uniqueness of CS as a context for studying undergraduate motivation. Background: Computing disciplines are increasingly important in preparing the future workforce. It is imperative that CS educators understand how to motivate students and enhance student outcomes. Synthesizing findings across multiple studies allows for the emergence of new insights into student motivation and SRL. Research Questions: Which aspects of students' motivation and SRL are predictive of achievement and retention in CS and how can findings inform CS education? Methodology: The primary methodology is a comprehensive review of seven years of research on undergraduate CS education. Studies use a variety of analysis techniques, examine a range of constructs, and include multiple introductory and advanced CS courses. Studies of relationships between variables and change over time were conducted. Findings: The present synthesis of studies on motivation and SRL highlights the complex, counter-intuitive, and positive aspects of student motivation in CS.

关键词： Computer science   gender equity   gender gap   science   STEM   women in computing  

摘要： ACM-W is the community within the Association for Computing Machinery (ACM) that is dedicated to issues of gender equality in Computer Science. ACM-W works globally to support, celebrate and advocate for the full participation of women in all aspects of the computing field. This article presents a brief history of ACM-W with an emphasis on the global growth of the organization. A summary of the primary programs of ACM-W is provided to further highlight the global impact of our work. Also included are examples of how ACM-W is partnering with other computing and scientific organizations to realize greater impact in the arena of gender equality.

摘要： Takiyah Nur Amin’s citation of Alice Walker directly speaks to the need for this volume. Alice Walker once said, “People are known by the records they keep. If it’s not in the records, it will be said that it did not happen” (237).Are You Entertained? Black Popular Culture in the Twenty-First Century, an anthology edited by Simone C. Drake and Dwan K. Henderson, creates a reflective record of a wide range of Black art and popular culture in the twenty-first century. The methodologies of this text work across genres, including fiction, professional sports, cartoons, cabaret performances, and beyond, to highlight, examine, and theorize the “Black” in Black popular culture. Various mediums are analyzed, encompassing social media, radio, television, cartoons, professional athletics, theater, dance, and more. Significant cultural milestones include Grammy performances, the first Black US president, and big-box movies that feature Blackness and Black people to create and perpetuate the popular culture. From this eclectic Africanist matrix, the authors probe how Black entertainment can be a tool of resistance, embodiment, and *** Omi and Howard Winant’s racial formation theory foregrounds the book’s analysis of race generally and the ways in which Blackness specifically is socially constructed and lived out daily by Black people. The authors confirm a race-conscious framework and a rejection of a post-racial ideology. Since Blackness has been mass-produced, commodified, and consumed to accommodate the increased desire for information and profit of non-Black people, the contributions investigate various ways Blackness has transcended Black bodies and entered American culture. Due to the long history of erasure and invisibility of the contributions of Black people in the entertainment industry, scholarship and records focused on critically engaging Blackness become crucial. Interdisciplinary explorations of agency and power within Black bodies and Black art h

关键词： Turing machines  

摘要： The quest to understand consciousness, once the purview of philosophers and theologians, is now actively pursued by scientists of many stripes. We examine consciousness from the perspective of Theoretical Computer Science (TCS), a branch of mathematics concerned with understanding the underlying principles of computation and complexity, including the implications and surprising consequences of resource limitations. We are inspired by Alan Turing's simple yet powerful definition of a computer, the Turing Machine (TM), and by the Global Workspace Theory (GWT) of consciousness originated by cognitive neuroscientist Bernard Baars and further developed by him, Stanislas Dehaene, Jean-Pierre Changeux, George Mashour and others. We are not looking for a complex model of the brain nor of cognition but for a simple substrate independent computational model of (the admittedly complex concept of) consciousness. We do this by defining the Conscious Turing Machine (CTM), also called a Conscious AI, and then we define consciousness and related notions in the CTM. While these are only mathematical TCS definitions, we suggest why the CTM has feelings of consciousness. The TCS perspective provides a simple framework to employ tools from computational complexity theory and machine learning to help us understand consciousness and related concepts. Previously we explored explanations for the feelings of pain and pleasure in the CTM. Here we consider additional phenomena generally associated with consciousness, again from the perspective of the CTM. We start with three examples related to vision (blindsight, inattentional blindness, and change blindness), then follow with a discussion of dreams, altered states, and free will. We give explanations derived from the model and draw confirmation from consistencies at a high level - well above the level of neurons - with the psychology and neuroscience literature. This paper is intended to be an introduction to a much-expanded monograph, in p

关键词： Systolic arrays  

摘要： This paper proposes a novel hardware accelerator for inference of sparse convolutional neural networks (CNNs) by building a hardware unit to perform Image to Column (IM2COL) transformation of the input feature map coupled with a systolic array-based general matrix-matrix multiplication (GEMM) unit. Our design carefully overlaps the IM2COL transformation with the GEMM computation to maximize *** propose a novel design for the IM2COL unit that uses a set of distributed local memories connected by a ring network, which improves energy efficiency and latency by streaming the input feature map only once. The systolic array based GEMM unit in the accelerator can be dynamically configured as multiple GEMM units with square systolic arrays or as a single GEMM unit with a tall systolic array. This dynamic reconfigurability enables effective pipelining of IM2COL and GEMM operations and attains high processing element utilization for a wide range of CNNs. Further, our accelerator is sparsity-aware, improving performance and energy efficiency by effectively mapping the sparse feature maps and weights to the processing elements, skipping ineffectual operations and unnecessary data movements involving zeros. Our prototype, SPOTS, is on average 1.74× and 2.16× faster than two systolic array-based hardware accelerators, Eyeriss and Gemmini, respectively. SPOTS is also 78×, and 12× more energy-efficient when compared to CPU and GPU implementations, respectively. Copyright © 2021, The Authors. All rights reserved.

关键词： Coal   Spinning   Rails   Gold   Electrical engineering   Voting   Production  

摘要： In electing me your president for the first year of the existence of the South African Institute of Electrical Engineers, an honour has been conferred on me of which I am very proud, and for which I have to thank you. Feeling strongly as I do that this Institute is even now, at such a young stage, fairly representative of the Electrical Engineers of South Africa, I feel doubly honoured by such election and I will endeavour to further the interests of the Institute as far as my ability, enthusiasm for the profession, and the time which can be taken from a somewhat busy life, will permit.