Deep neural networks are known for their capabilities for automatic feature learning from data. For this reason, previous research has tended to interpret deep learning techniques as data-driven methods, while few advances have been made from knowledge-driven perspectives. We propose to design a semantic rich deep learning model from a knowledge driven perspective, by introducing formal semanti...

Numerous groups have applied a variety of deep learning techniques to computer vision problems in highway perception scenarios. In this paper, we presented a number of empirical evaluations of recent deep learning advances. Computer vision, combined with deep learning, has the potential to bring about a relatively inexpensive, robust solution to autonomous driving. To prepare deep learning for ...

Deep learning has emerged as a new area of machine learning research. It has been successfully applied to several fields such as images, sounds, text and motion. In this project, deep learning was applied to protein interaction prediction and compared with support vector machines. Deep learning was shown to have a good performance as well as SVM with Fisher score features.

digital libraries offer opportunities for e-learning that are not possible in their physical counterparts. digital libraries complement other learning environments, such as those provided in distance education and courses offered online. like e-learning environments, they provide flexibility of time and place. digital libraries have the potential to offer unprecedented resources to support e-le...

The present study compared non-traditional teaching and learning methods (involving project-based learning) with traditional methods, and examined their effect on students’ approaches to learning. The study also investigated whether particular teaching, learning and assessment (TLA) methodologies contributed to deeper approaches to learning. Seventy psychology students participated in the study...

In problem-based learning (PBL), implemented worldwide, students learn by discussing professionally relevant problems enhancing application and integration of knowledge, which is assumed to encourage students towards a deep learning approach in which students are intrinsically interested and try to understand what is being studied. This review investigates: (1) the effects of PBL on students' d...

considering the essential role that product development plays in fast- growing firms learning how to perform its activities can be highly valued, whereas product development activities are per se a proper context for knowledge acquisition. in this study, the narrative approach and the technique of deep and targeted interviews have been used to narrate the stories expressed by nine of the sales ...

Deep learning systems have dramatically improved the accuracy of speech recognition, and various deep architectures and learning methods have been developed with distinct strengths and weaknesses in recent years. How can ensemble learning be applied to these varying deep learning systems to achieve greater recognition accuracy is the focus of this paper. We develop and report linear and log-lin...