Perhaps the single largest data source in the world is the world wide web. Heterogeneous and unstructured nature of the data on web has challenged mining the web. Practical needs to extract textual information and unseen patterns continue to drive the research interest in text mining. Faultless categorization of texts can be better performed by machine learning techniques. In this paper we pres...

Coordinate descent (CD) algorithms have become the method of choice for solving a number of machine learning tasks. They are particularly popular for training linear models, including linear support vector machine classification, LASSO regression, and logistic regression. We propose an extension of the CD algorithm, called the adaptive coordinate frequencies (ACF) method. This modified CD schem...

In this paper we introduce DiffSharp, an automatic differentiation (AD) library designed with machine learning in mind. AD is a family of techniques that evaluate derivatives at machine precision with only a small constant factor of overhead, by systematically applying the chain rule of calculus at the elementary operator level. DiffSharp aims to make an extensive array of AD techniques availab...

While machine learning tools have been rapidly advancing, the majority of neural decoding approaches still use last century's methods. Improving the performance of neural decoding algorithms allows us to better understand what information is contained in the brain, and can help advance engineering applications such as brain machine interfaces. Here, we apply modern machine learning techniques, ...

In this paper, an extreme learning machine with an automatic segmentation algorithm is applied to heart disorder classification by heart sound signals. From continuous heart sound signals, the starting points of the first (S1) and the second heart pulses (S2) are extracted and corrected by utilizing an inter-pulse histogram. From the corrected pulse positions, a single period of heart sound sig...

Machine learning methods have found many applications in Raman spectroscopy, especially for the identification of chemical species. However, almost all of these methods require non-trivial preprocessing such as baseline correction and/or PCA as an essential step. Here we describe our unified solution for the identification of chemical species in which a convolutional neural network is trained t...

In this project, we applied two machine learning techniques: CNN (Convolutional Neural Network) and SVM (Support Vector machine) to build an image aesthetic evaluating system. And we have achieved an 5-folder cross validation accuracy of above 99% by using CNN implemented in Torch. In the ‘Introduction’ section, a brief background of the problem and an introduction of our system are given. In t...

Data-target pairing is an important step towards multi-target localization for the intelligent operation of unmanned systems. Target localization plays a crucial role in numerous applications, such as search, and rescue missions, traffic management and surveillance. The objective of this paper is to present an innovative target location learning approach, where numerous machine learning approac...