Speech emotion recognition (SER) is an active research area in affective computing. Recognizing emotions from speech signals helps to assess human behaviour, which has promising applications the of human-computer interaction. The performance deep learning-based SER methods relies heavily on feature learning. In this paper, we propose SCAR-NET, improved convolutional neural network, extract emot...

Most machine learning algorithms are lazy: they extract from the training set the minimum information needed to predict its labels. Unfortunately, this often leads to models that are not robust when features are removed or obscured in future test data. For example, a backprop net trained to steer a car typically learns to recognize the edges of the road, but does not learn to recognize other fe...

A popular approach to training feed-forward nets is to treat the problem of adaptation as a function approximation and to use curve fitting techniques. We discuss here the problems which the use of pure curve fitting techniques entail for the generalization capability and robustness of the net. These problems are in general inherently associated with the use of pure supervised learning techniqu...

A flood is an overflow of water that swamps dry land. The gravest effects flooding are the loss human life and economic losses. An early warning these events can be very effective in minimizing Social media websites such as Twitter Facebook quite efficient dissemination information pertinent to any emergency. Users on social networking sites share both textual rich content images videos. Multim...

The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations. However, even the largest public datasets only provide samples with pixel-level annotations for rather limited semantic categories. Such data scarcity critically limits scalability and applicability of semantic segmentation models in real applications. In this paper, ...