Sparse neural networks attract increasing interest as they exhibit comparable performance to their dense counterparts while being computationally efficient. Pruning the is among most widely used methods obtain a sparse network. Driven by high training cost of such that can be unaffordable for low-resource device, sparsely from scratch has recently gained attention. However, existing algorithms ...

The traditional co-training algorithm, which needs a great number of unlabeled examples in advance and then trains classifiers by iterative learning approach, is not suitable for online learning of classifiers. To overcome this barrier, we propose a novel semi-supervised learning algorithm, called MAPACo-Training, by combining the co-training with the principle of Maximum A Posteriori adaptatio...

Machine learning techniques have facilitated image retrieval by automatically classifying and annotating images with keywords. Among them Support Vector Machines (SVMs) are used extensively due to their generalization properties. However, SVM training is notably a computationally intensive process especially when the training dataset is large. In this thesis distributed computing paradigms have...