教学课程资源库 更多>>

关键词： Transfer learning   Bridges   Metalearning   Adaptation models   Computer science   Training   Task analysis   heterogeneous label spaces   selective random walk  

摘要： Transfer learning has been widely used in different scenarios, especially in those lacking enough labeled data. However, most of the existing transfer learning methods are based on the assumption that the source and target domains should share the label space entirely or partially, which greatly limits their application scopes. In this article, a Selective Random Walk (SRW) method for transfer learning in heterogeneous label spaces is proposed to make full use of unlabeled auxiliary data, which acts as a bridge for knowledge transfer from the source domain to the target domain. The proposed SRW method can explicitly identify transfer sequences between source and target instances via auxiliary instances based on random walk techniques. Since not all of the transfer sequences generated by random walk are credible for the target task, the SRW method can learn to weight transfer sequences adaptively. Based on the weights of the transfer sequences, the SRW method leverages knowledge by forcing adjacent data points in the transfer sequence to be similar and making the target data point in the sequence represented by other data points in the same sequence. Experiments show that the SRW method outperforms state-of-the-art models in plenty of transfer learning tasks with heterogeneous label spaces constructed within and across several benchmark datasets.

关键词： capital punishment   Hobbes   jurisprudence   Hegel   Foucault   equity   Supreme Court of India  

摘要： This paper attempts to establish that capital punishment is not rational and cannot be rationalized without suicidally destroying the very ground on which lawful and rational punishment bases itself. It argues that in capital punishment, just as in any lawful punishment, the criminal is both held (humanly) rational and therefore culpable. But, unlike other forms of punishment, in capital punishment, the condemned is at the same time, held as irrational and irredeemable, beyond reform, and therein outside the ambit of rationality and humanity. In this sense a fundamental aporia is reached in rationalizing capital punishment because of the contradiction between the basis of punishment (the human as rational) and its operational logic (the condemned person as beyond reform therein irrational). Expressed another way, the judge proclaims a form of infallibility in their reasoning where the incorrigibility of the judgment is horrifically demonstrated and ironically reflected (and projected) in the incorrigibility of the condemned. This broad argument is pursued in two parts;one part interprets canonical texts such as Hobbes, Hegel and Foucault, while the second part interprets the Supreme Court of India's jurisprudence around the death penalty. While these are very different discourses it will be shown that they share much common ground in their expressing-and negotiating-the fundamental problem as described above.

关键词： PRIP-2023   image analysis   pattern recognition   artificial intelligence   information processing   computer science  

摘要： The main scientific results of the 16th International Conference on Pattern Recognition and Information Processing (PRIP-2023), Minsk, Republic of Belarus, October 2023, are reviewed and analyzed. The history of this series of conferences is outlined, and its significant role in the development of the theory and practice of image analysis, pattern recognition, and artificial intelligence is indicated. A list of articles in the special issue is provided, prepared from reports selected by the PRIP-2023 Program Committee.

关键词： Agile software development   computer science   computer science education   course design   design process   instruction   machine learning (ML)   software engineering (SE)  

摘要： Contribution: A novel undergraduate course design at the intersection of software engineering (SE) and machine learning (ML) based on industry-reported ***: ML professionals report that building ML systems is different enough that we need new knowledge about how to infuse ML into software production. For instance, various experts need to be deeply involved with these SE projects, such as business analysts, data scientists, and *** outcomes: The creation of a table detailing and matching industry challenges with course learning objectives, course topics, and related *** design: Course content was derived from interviewing industry professionals with related experience as well as surveying undergraduate SE students. The proposed course style is designed to emulate real-world ML-based ***: Industry-derived content for a pilot undergraduate course has been successfully crafted at the intersection of SE and ML.

关键词： Computer science   Machine learning   Society  

关键词： Computer science   Engineering  

摘要： The computer vision algorithms used currently in advanced driver assistance systems rely on image-based RGB cameras, leading to a critical bandwidth-latency trade-off for delivering safe driving experiences. To address this, event cameras have emerged as alternative vision sensors. Event cameras measure the changes in intensity asynchronously, offering high temporal resolution and sparsity, markedly reducing bandwidth and latency requirements 1 . Despite these advantages, event-camera-based algorithms are either highly efficient but lag behind image-based ones in terms of accuracy or sacrifice the sparsity and efficiency of events to achieve comparable results. To overcome this, here we propose a hybrid event- and frame-based object detector that preserves the advantages of each modality and thus does not suffer from this trade-off. Our method exploits the high temporal resolution and sparsity of events and the rich but low temporal resolution information in standard images to generate efficient, high-rate object detections, reducing perceptual and computational latency. We show that the use of a 20 frames per second (fps) RGB camera plus an event camera can achieve the same latency as a 5,000-fps camera with the bandwidth of a 45-fps camera without compromising accuracy. Our approach paves the way for efficient and robust perception in edge-case scenarios by uncovering the potential of event cameras 2 . Use of a 20 frames per second (fps) RGB camera plus an event camera can achieve the same latency as a 5,000-fps camera with the bandwidth of a 45-fps camera without compromising accuracy.

关键词： Forecasting  

摘要： A career is a crucial aspect for any person to fulfill their desires through hard work. During their studies, students cannot find the best career suggestions unless they receive meaningful guidance tailored to their skills. Therefore, we developed an AI-assisted model for early prediction to provide better career suggestions. Although the task is difficult, proper guidance can make it easier. Effective career guidance requires understanding a student’s academic skills, interests, and skill-related activities. In this research, we collected essential information from Computer Science (CS) and Software Engineering (SWE) students to train a machine learning (ML) model that predicts career paths based on students’ career-related information. To adequately train the models, we applied Natural Language Processing (NLP) techniques and completed dataset pre-processing. For comparative analysis, we utilized multiple classification ML algorithms and deep learning (DL) algorithms. This study contributes valuable insights to educational advising by providing specific career suggestions based on the unique features of CS and SWE students. Additionally, the research helps individual CS and SWE students find suitable jobs that match their skills, interests, and skill-related activities. © 2024, CC BY-SA.

关键词： Students  

摘要： Contribution: The combination of ChatGPT with traditional learning resources is very effective in computer science education. High-performing students are the ones who are using ChatGPT the most. So, a new digital trench could be rising between these students and those with lower degree of fundamentals and worse prompting skills, who may not take advantage of all the ChatGPT possibilities. Background: The irruption of GenAI such as ChatGPT has changed the educational landscape. Therefore, methodological guidelines and more empirical experiences in computer science education are needed to better understand these tools and know how to use them to their fullest potential. Research Questions: This article addresses three questions. The first two explore the degree of use and perceived usefulness of ChatGPT among computer science students to learn database administration, where as the third one explore how the utilization of ChatGPT can impact academic performance. Methodology: This contribution presents an exploratory and correlational study conducted with 37 students who used ChatGPT as a support tool to learn database administration. The student's grades and a comprehensive questionnaire were employed as research instruments. Findings: The obtained results indicate that traditional learning resources, such as teacher's explanations and student's reports, were widely used and correlated positively with student's grade. The usage and perceived utility of ChatGPT were moderate, but positive correlations between student's grade and ChatGPT usage were found. Indeed, a significantly higher use of this tool was identified among the group of outstanding students. © 2024, CC BY-NC-ND.

关键词： Virtual reality  

摘要： This paper represents a pilot study examining learners who are new to computer science (CS). Subjects are taught to program in one of two virtual reality (VR) applications developed by the researcher that use interactable objects representing programming concepts. The different versions are the basis for two experimental groups. One version of the app uses textual code for the interactable programming objects and the other version uses everyday objects as visual metaphors for the CS concepts the programming objects represent. For the two experimental groups, the study compares the results of self-efficacy surveys and CS knowledge tests taken before and after the VR activity intervention. An attitudinal survey taken after the intervention examines learners' sense of productivity and engagement with the VR activity. While further iterations of the study with a larger sample size would be needed to confirm any results, preliminary findings from the pilot study suggest that both methods of teaching basic programming concepts in VR can lead to increased levels of self-efficacy and knowledge regarding CS, and can contribute toward productive mental states. © 2024, CC BY.

关键词： Computer vision  

摘要： It is undeniable that citizen science contributes to the advancement of various fields of study. There are now software tools that facilitate the development of citizen science apps. However, apps developed with these tools rely on individual human skills to correctly collect useful data. Machine learning (ML)-aided apps provide on-field guidance to citizen scientists on data collection tasks. However, these apps rely on server-side ML support, and therefore need a reliable internet connection. Furthermore, the development of citizen science apps with ML support requires a significant investment of time and money. For some projects, this barrier may preclude the use of citizen science effectively. We present a platform that democratizes citizen science by making it accessible to a much broader audience of both researchers and participants. The SmartCS platform allows one to create citizen science apps with ML support quickly and without coding skills. Apps developed using SmartCS have client-side ML support, making them usable in the field, even when there is no internet connection. The client-side ML helps educate users to better recognize the subjects, thereby enabling high-quality data collection. We present several citizen science apps created using SmartCS, some of which were conceived and created by high school students. © 2024, CC BY.