Heutagogy provides an approach to adult education that is based on learner determined learning and it recognises that this requires a transformation of learning processes beyond a teacher-delivered focus on content. B...
详细信息
ISBN:
(纸本)9781538678978
Heutagogy provides an approach to adult education that is based on learner determined learning and it recognises that this requires a transformation of learning processes beyond a teacher-delivered focus on content. But there are few guidelines or even descriptions of application of heutagogy to whole programmes of learning, and none on the application of this to computing Education. In this paper we describe a case study of an independent learning pathway approach whereby heutagogy is the underlying principle for work-based learning professional practice programmes for computing professionals. Questions for further development and research are discussed.
Comprehension of programming and programs is known to be a difficult task for many beginning students, with many computing courses showing significant drop out and failure rates. In this paper, we present a notional m...
详细信息
ISBN:
(纸本)9781509025046
Comprehension of programming and programs is known to be a difficult task for many beginning students, with many computing courses showing significant drop out and failure rates. In this paper, we present a notional machine implementation, Novis, to help with understanding of programming and its dynamics for beginning learners. The notional machine offers an abstraction of the physical machine designed for comprehension and learning purposes. Novis provides a real-time visualisation of this notional machine, and is integrated into BlueJ.
Source Code Authorship attribution (SCAA) is crucial for software classification because it provides insights into the origin and behavior of software. By accurately identifying the author or group behind a piece of c...
详细信息
Photoplethysmogram (PPG) signals are pivotal in cardiovascular monitoring, offering real-time insights into heart rate and oxygen saturation (SpO2). This study explores the creation of deep learning and machine learni...
详细信息
This paper introduces a new approach for the analysis of didactic transposition phenomenon in Computer Science education, and its foundations for the construction of teaching objects. Thus, two main scenarios were exp...
详细信息
ISBN:
(纸本)9781479999675
This paper introduces a new approach for the analysis of didactic transposition phenomenon in Computer Science education, and its foundations for the construction of teaching objects. Thus, two main scenarios were explored: teaching experiences on programming fundamentals at undergraduate level, and the construction and deployment of teaching objects which have been framed within the European project called Open Discovery Space for K-12 education, by using computing means. The description of experiences in both scenarios is documented according to the following schema: A theoretical background, the findings, and the statement of new proposals to improve teaching practices and the criteria for constructing teaching objects as conclusions of this paper.
The human brain, among the most complex and mysterious aspects of the body, harbours vast potential for extensive exploration. Unravelling these enigmas, especially within neural perception and cognition, delves into ...
详细信息
The efficient execution of attention-based transformers and large language models on traditional CPUs and GPUs presents significant challenges related to performance and energy efficiency. While innovative solutions l...
详细信息
ISBN:
(纸本)9798400710773
The efficient execution of attention-based transformers and large language models on traditional CPUs and GPUs presents significant challenges related to performance and energy efficiency. While innovative solutions like ASICs, FPGAs, and ReRAMs have been explored, the field of silicon photonics has emerged as a promising avenue for developing energy-efficient accelerators for deep AI models. Notably, existing endeavors in silicon photonics have predominantly concentrated on inference for deep AI algorithms, leaving a limited number of initiatives focused on creating comprehensive deep learning accelerators capable of real-time training for transformer-like algorithms. This paper utilizes the superior merits of silicon photonics to realize a full-fledged transformer accelerator equipped for both inference and training. Introducing PHOTRAN, an AI analog photonics accelerator, we harness silicon microdisk-based convolution, photonic phase-change memory-based cache, and dense-wavelength-division-multiplexing to achieve energy-efficient and ultrafast transformer acceleration. Through evaluations using a commercial CAD framework on benchmark models, including Vision Transformers and Large Language models, our results showcase the superior performance of PHOTRAN. This work underscores the significant potential of photonic computing for on-chip training of large deep AI models.
Various degradations available in historical document images pose challenges to automatic document restoration methods. Recent strides in deep learning and generative adversarial networks (GANs) for document analysis ...
详细信息
This research introduces a novel method for image enhancement and repair using Generative AI - Stable diffusion model. Unlike traditional techniques, it selectively masks and replaces areas to adjust aspect ratio whil...
详细信息
One of the reasons to have in-class quizzes or exercises is to ensure that students understand the lecture and to reinforce the most important concepts. In the past, students must rely on their class notes when workin...
详细信息
ISBN:
(纸本)9781479935918
One of the reasons to have in-class quizzes or exercises is to ensure that students understand the lecture and to reinforce the most important concepts. In the past, students must rely on their class notes when working on those exercises. In this study, we embarked on a practice to record and made available the in-class lectures to the students in near real-time. Students can then re-watch any part of a lecture to clarify or reinforce learned concepts asynchronously and autonomously.
暂无评论