In this paper, we propose a new information theoretic method for a linguistic rule acquisition problem, and demonstrate that a linguistic rule acquisition process is an instance of realization of information maximization. The new method is based upon unsupervised competitive learning. The unsupervised learning is needed because children acquire rules without any explicit instruction. In the exp...

Big sensor data provide significant potential for chemical fault diagnosis, which involves the baseline values of security, stability and reliability in chemical processes. A deep neural network (DNN) with novel active learning for inducing chemical fault diagnosis is presented in this study. It is a method using large amount of chemical sensor data, which is a combination of deep learning and ...

Unsupervised joint alignment of images has been demonstrated to improve performance on recognition tasks such as face verification. Such alignment reduces undesired variability due to factors such as pose, while only requiring weak supervision in the form of poorly aligned examples. However, prior work on unsupervised alignment of complex, real-world images has required the careful selection of...

We study detecting cell events in phase-contrast microscopy sequences from few annotations. We first detect event candidates from the intensity difference of consecutive frames, and then train an unsupervised novelty detector on these candidates. The novelty detector assigns each candidate a degree of surprise. We annotate a tiny number of candidates chosen according to the novelty detector’s o...

A significant cost in obtaining acoustic training data is the generation of accurate transcriptions. When no transcription is available, unsupervised training techniques must be used. Furthermore, the use of discriminative training has become a standard feature of state-ofthe-art large vocabulary continuous speech recognition (LVCSR) system. In unsupervised training, unlabelled data are recogni...

Text clustering is unsupervised machine learning method.It needs representation of objects and similarity measure. which compares distribution of features between objects. For the high dimensionality of feature space performance of clustering algorithms decreases.Two techniques are used to deal with this problem: feature extraction and feature selection.In this paper, we describe the hybrid met...

The task of matching co-referent records is known among other names as record linkage. For large record-linkage problems, often there is little or no labeled data available, but unlabeled data shows a reasonably clear structure. For such problems, unsupervised or semi-supervised methods are preferable to supervised methods. In this paper, we describe a hierarchical graphical model framework for...