Although animations are believed to be effective in learning and teaching, several studies have failed to confirm this. Nevertheless, animations might be more attractive and motivating. Fourth and sixth grade students learned the operation of a bicycle pump from graphics that were: (i) presented simultaneously; (ii) presented successively; (iii) self-paced, or (iv) animated. The presentation mo...

The least squares method with deep neural networks as function parametrization has been applied to solve certain high-dimensional partial differential equations (PDEs) successfully; however, its convergence is slow and might not be guaranteed even within a simple class of PDEs. To improve the network-based model, we introduce novel self-paced learning framework, SelectNet, which quantifies diff...

PURPOSE This study compared cognitive (attention, learning, and memory) and typing outcomes during slow treadmill walking or sitting. Seventy-five healthy individuals were randomly assigned to a treadmill walking group (n=37; 23 female) or sitting group (n=38; 17 female). METHODS The treadmill walking group completed a series of tests while walking at 1.5 mph. The sitting group performed the ...

Zero-shot learning (ZSL) endows the computer vision system with the inferential capability to recognize new categories that have never seen before. Two fundamental challenges in it are visual-semantic embedding and domain adaptation in cross-modality learning and unseen class prediction steps, respectively. This paper presents two corresponding methods named Adaptive STructural Embedding (ASTE)...

Learning with computers is typically self-paced. Appraisal of the learner’s experience is therefore crucial for making machine-learner interactions ‘truly intelligent’ and instinctive. As a significant aspect of Affective Learning, affect recognition needs to be considered in light of its implications and appliance to computer based learning environments. Drawing on this motivation, I propose t...

The present study aimed at examining the oscillatory brain-electric correlates of human operant learning using high-density electroencephalography (EEG). Induced gamma-band activity (GBA) was studied using a fixed-interval reinforcement schedule with a variable limited hold period, which was decreased depending on response accuracy. Thus, participants' behavior was shaped during the course of t...

Deep learning (DL) is inherently subject to the requirement of a large amount well-labeled data, which expensive and time-consuming obtain manually. In order broaden reach DL, leveraging free web data becomes an attractive strategy alleviate issue scarcity. However, directly utilizing collected train deep model ineffective because mixed noisy data. To address such problems, we develop novel bid...

Abstract Existing re-identification (re-ID) methods rely on a large number of cross-camera identity tags for training, and the data annotation process is tedious time-consuming, resulting in difficult deployment real-world re-ID applications. To overcome this problem, we focus single camera training (SCT) setting, where each annotated camera. Since there no across cameras, it takes much less ti...