This article reflects on effective supervision and possible guidance for enhancing quality of doctoral research in the computerscience and engineering field. The aims of this study are (1) to understand supervision a...
详细信息
This innovative practice full paper presents an empirical study aimed at evaluating the potential of ChatGPT, an advanced AI-driven chatbot, as a supplementary educational tool in undergraduate computerscience and So...
详细信息
ISBN:
(纸本)9798350351507
This innovative practice full paper presents an empirical study aimed at evaluating the potential of ChatGPT, an advanced AI-driven chatbot, as a supplementary educational tool in undergraduate computerscience and Software engineering (CSSE) courses. The study, initiated in the summer of 2023, focused on assessing ChatGPT's capabilities in generating accurate and complete computer code, identifying and rectifying code defects (bugs), and its scalability in handling larger programs. To achieve this, we conducted a series of experiments with ChatGPT. In one experiment, we introduced bugs into small programs from introductory CSSE courses. ChatGPT was tasked with detecting these defects and providing recommendations for fixing them. We evaluated ChatGPT's effectiveness in bug detection, the quality of its recommendations, and the completeness of the proposed solutions. We sought answers to questions such as whether ChatGPT found all injected defects, provided appropriate recommendations, and delivered high-quality solutions based on criteria like code completeness, size, complexity, and readability. In another experiment, ChatGPT was asked to generate code for assignments from previous CSSE courses, including Intro to computerscience and Programming in C++, Intro to Python Programming, and Object-Oriented Programming and Data Structures using Java. We assessed the generated code's correctness and quality in comparison to student-written code. Similarly, in a third experiment, we evaluated ChatGPT's ability to generate larger programs using requirement specifications from an upper-division CSSE course on Agile Software engineering. Analyzing both qualitative and quantitative data from these experiments during the summer, we determined that ChatGPT showed promise as an educational tool. Consequently, we developed a plan to integrate ChatGPT into select CSSE courses for the fall semester of 2023. Specifically, ChatGPT was integrated into two of our introductory CSSE cou
In partnership with the Silicon Valley engineering Tech Pathways (SVETP), Skyline College developed and began piloting the engineering & Tech Scholars Program (ETS) program in Fall 2016. The ETS program is a cohor...
Constructing an effective common latent embedding by aligning the latent spaces of cross-modal variational autoencoders（VAEs） is a popular strategy for generalized zero-shot learning（GZSL）. However, due to the lac...
详细信息
Constructing an effective common latent embedding by aligning the latent spaces of cross-modal variational autoencoders（VAEs） is a popular strategy for generalized zero-shot learning（GZSL）. However, due to the lack of fine-grained instance-wise annotations, existing VAE methods can easily suffer from the posterior collapse problem. In this paper, we propose an innovative asymmetric VAE network by aligning enhanced feature representation（AEFR） for GZSL. Distinguished from general VAE structures, we designed two asymmetric encoders for visual and semantic observations and one decoder for visual reconstruction. Specifically, we propose a simple yet effective gated attention mechanism（GAM） in the visual encoder for enhancing the information interaction between observations and latent variables, alleviating the possible posterior collapse problem effectively. In addition, we propose a novel distributional decoupling-based contrastive learning（D2-CL） to guide learning classification-relevant information while aligning the representations at the taxonomy level in the latent representation space. Extensive experiments on publicly available datasets demonstrate the state-of-the-art performance of our method. The source code is available at https://***/seeyourmind/AEFR.
Communication is a key element for classroom teaching and group project management in higher education. In this paper, we describe in detail how an online tool, Slack, helps improve communication and collaboration in ...
详细信息
Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inher...
详细信息
Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the ?0-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and *** algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.
Due to the probability characteristics of quantum mechanism, the combination of quantum mechanism and intelligent algorithm has received wide attention. Quantum dynamics theory uses the Schr?dinger equation as a quant...
详细信息
Due to the probability characteristics of quantum mechanism, the combination of quantum mechanism and intelligent algorithm has received wide attention. Quantum dynamics theory uses the Schr?dinger equation as a quantum dynamics equation. Through three approximation of the objective function, quantum dynamics framework(QDF) is obtained which describes basic iterative operations of optimization algorithms. Based on QDF, this paper proposes a potential barrier estimation(PBE) method which originates from quantum mechanism. With the proposed method, the particle can accept inferior solutions during the sampling process according to a probability which is subject to the quantum tunneling effect, to improve the global search capacity of optimization *** effectiveness of the proposed method in the ability of escaping local minima was thoroughly investigated through double well function(DWF), and experiments on two benchmark functions sets show that this method significantly improves the optimization performance of high dimensional complex functions. The PBE method is quantized and easily transplanted to other algorithms to achieve high performance in the future.
The freshman program is designed to introduce engineering principles through hands-on experience, establish a sense of community, develop an understanding of how to be successful in studying engineering, and to foster...
详细信息
The freshman program is designed to introduce engineering principles through hands-on experience, establish a sense of community, develop an understanding of how to be successful in studying engineering, and to foster collaboration among students through cooperative teaming. This paper presents an overview of the program that has evolved over the past six years.
The pixel-wise dense prediction tasks based on weakly supervisions currently use Class Attention Maps(CAMs)to generate pseudo masks as ***,existing methods often incorporate trainable modules to expand the immature cl...
详细信息
The pixel-wise dense prediction tasks based on weakly supervisions currently use Class Attention Maps(CAMs)to generate pseudo masks as ***,existing methods often incorporate trainable modules to expand the immature class activation maps,which can result in significant computational overhead and complicate the training *** this work,we investigate the semantic structure information concealed within the CNN network,and propose a semantic structure aware inference(SSA)method that utilizes this information to obtain high-quality CAM without any additional training ***,the semantic structure modeling module(SSM)is first proposed to generate the classagnostic semantic correlation representation,where each item denotes the affinity degree between one category of objects and all the ***,the immature CAM are refined through a dot product operation that utilizes semantic structure ***,the polished CAMs from different backbone stages are fused as the *** advantage of SSA lies in its parameter-free nature and the absence of additional training costs,which makes it suitable for various weakly supervised pixel-dense prediction *** conducted extensive experiments on weakly supervised object localization and weakly supervised semantic segmentation,and the results confirm the effectiveness of SSA.
暂无评论