Search academic resources

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural...

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors ...

While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics tod...

"This thesis investigates the application of machine learning methods to the task of deforestation monitoring using time-series satellite data. The objective is to assess how different algorithmic approaches perform in d...

Abstract Individualized educational management cannot be avoided in meeting various learner needs in cases where teaching strategies are changed in line with the performance trends and preferences of students. Reinforcem...

Abstract With a growing number of institutions involved in the global education market, it has become increasingly challenging to verify the authenticity of academic documents and to match them between universities. The ...

Photonic reservoir computing has been intensively investigated to solve machine learning tasks effectively. A simple learning procedure of output weights is used for reservoir computing. However, the lack of training of ...

Abstract Matching college students with appropriate innovative training projects is a challenging task that often relies on static assignment techniques, which overlook individual interests, skills, and learning styles. ...

Despite significant progress in autonomous vehicles (AVs), the development of driving policies that ensure both the safety of AVs and traffic flow efficiency has not yet been fully explored. In this paper, we propose an ...

Purpose – This study aims to determine the effectiveness of NHT Cooperative Learning assisted by Lumi Education in improving the abductive reasoning skills of junior high school students in science lessons on substance...

Design studio projects are fundamental to environmental education, as they facilitate the integration of theoretical knowledge with creative practice through experiential, collaborative, and reflective learning. This s...

A partir dos anos 70, emergiram dois referenciais para se investigar as abordagens dos alunos à aprendizagem. O primeiro, qualitativo, baseado nos estudos de Marton e colaboradores; o outro, desenvolvido por Biggs e col...

The article throws the light on the problem of developing students’ critical thinking skills through interactive learning. The latter offers numerous benefits for students'soft skills improvement. It requires students ...

Abstract This study examined whether defensive pessimism-related processes influence university students’ approaches to learning, psychological well-being, and academic performance indirectly through academic procrasti...

With advancements in autonomous driving technology, to minimize the decision-making disparities between human drivers and intelligent vehicles, the need for anthropomorphism and personalization in intelligent vehicles ha...

Blended and flipped classroom pedagogical models are recognised as having the potential to deepen and enrich student learning while also being a more engaging learning experience (Partridge, Ponting, & McCay, 2011). E-le...

We present a highly accurate single-image superresolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification [19]. We find increasing our network depth sho...

Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful intermediate representations. We intr...

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where th...

Rich in multiple strategic rare metals, deep-sea manganese nodules constitute an essential mineral resource for balancing terrestrial resource supply and demand and facilitating the global energy transition. Accurate pre...

Study abroad has been a matter of concern in sociolinguistics for a few decades now. Nevertheless, research on study abroad has rarely combined the study of sociolinguistic aspects with the analysis of perceived language...