Machine hearing is an emerging research field that is analogous to machine vision in that it aims to equip computers with the ability to hear and recognise a variety of sounds. It is a key enabler of natural human-computer speech interfacing, as well as in areas such as automated security surveillance, environmental monitoring, smart homes/buildings/cities. Recent advances in machine learning a...

Representation learning, especially which by using deep learning, has been widely applied in classification. However, how to use limited size of labeled data to achieve good classification performance with deep neural network, and how can the learned features further improve classification remain indefinite. In this paper, we propose Horizontal Voting Vertical Voting and Horizontal Stacked Ense...

Deep neural networks have become increasingly more popular under the name of deep learning recently due to their success in challenging machine learning tasks. Although the popularity is mainly due to the recent successes, the history of neural networks goes as far back as 1958 when Rosenblatt presented a perceptron learning algorithm. Since then, various kinds of artificial neural networks hav...

Hyperspectral data is not linearly separable, and it has a high characteristic dimension. This paper proposes a new algorithm that combines a deep belief network based on the Boltzmann machine with a self-organizing neural network. The primary features of the hyperspectral image are extracted with a deep belief network. The weights of the network are fine-tuned using the labeled sample. Feature...

Recently neural networks and multiple instance learning are both attractive topics in Artificial Intelligence related research fields. Deep neural networks have achieved great success in supervised learning problems, and multiple instance learning as a typical weakly-supervised learning method is effective for many applications in computer vision, biometrics, nature language processing, etc. In...

The work presented here applies deep learning to the task of automated cardiac auscultation, i.e. recognizing abnormalities in heart sounds. We describe an automated heart sound classification algorithm that combines the use of time-frequency heat map representations with a deep convolutional neural network (CNN). Given the cost-sensitive nature of misclassification, our CNN architecture is tra...

Heart sounds classification plays an important role in cardiovascular disease detection. Currently, deep learning methods for heart sound with heavy parameters consumption cannot be deployed environments limited memory and computational budgets. Besides, de-noising of signals (HSSs) can affect accuracy classification, because erroneous removal meaningful components may lead to distortion. In th...

Deep learning is a growing trend in computing. It is an improvement to artificial neural network. Deep Neural Networks are used in image classification, detection and segmentation. In this paper, an overview is carried out about the usage of deep neural network in various areas of image computing including image quality assessment, document imaging, object recognition, medical imaging, content ...

Aalto University, P.O. Box 11000, FI-00076 Aalto www.aalto.fi Author Kyunghyun Cho Name of the doctoral dissertation Foundations and Advances in Deep Learning Publisher Unit Department of Information and Computer Science Series Aalto University publication series DOCTORAL DISSERTATIONS 21/2014 Field of research Machine Learning Manuscript submitted 2 September 2013 Date of the defence 21 March ...