Convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks. In order to distinguish the reliable data from the noisy and confusing data, we improve CNNs with self-paced learning (SPL) for enhancing the learning robustness of CNNs. In the proposed self-paced convolutional network (SPCN), each sample is assigned to a weight to reflect the easines...

Continual learning algorithms which keep the parameters of new tasks close to that previous tasks, are popular in preventing catastrophic forgetting sequential task settings. However, 1) performance for continual learner will be degraded without distinguishing contributions previously learned tasks; 2) computational cost greatly increased with number since most existing need regularize all when...

Accurately assessing the physiological status of firefighters during work in the heat is critical to ensuring their safety. Evaluating core temperatures (Tc) in the field is problematic due to cost and limitations in technology and accuracy. As such, fire services rely on individual perceptions of wellbeing. The present study aimed to establish whether perceptual responses measured using the pe...

in recent years, work for the information profession has become characterized by fast-paced change and new skills requirements. this transformation has been brought about by the constant emergence of relevant new technologies. in this paper, ict skills for professionals in developing countries are examined and nigeria research project is mentioned as an example. one of the important implication...