With the increasing demand of multimedia information retrieval, such as image and video retrieval from the Web, there is a need to find ways to train a classifier when the training dataset is combined with a small number of labelled data and a large number of unlabeled one. Traditional supervised or unsupervised learning methods are not suited to solving such problems particularly when the prob...

Fast and eeective unsupervised clustering is a fundamental tool in unsupervised learning. Here is a new method to explore large datasets that enjoys many favorable properties. It is fast and eeective, and produces a hierarchical structure on the underlying dataset, without using a training set. It also yields auxiliary information on the signiicance of the diierent attributes.

An inescapable bottleneck with learning from large data sets is the high cost of labeling training data. Unsupervised learning methods have promised to lower the cost of tagging by leveraging notions of similarity among data points to assign tags. However, unsupervised and semi-supervised learning techniques often provide poor results due to errors in estimation. We look at methods that guide t...

We describe an unsupervised learning technique to facilitate automated creation of jazz melodic improvisation over chord sequences. Specifically we demonstrate training an artificial improvisation algorithm based on unsupervised learning using deep belief nets, a form of probabilistic neural network based on restricted Boltzmann machines. We present a musical encoding scheme and specifics of a ...

In clustering (also known as unsupervised learning and class discovery), the classes are unknown a priori and need to be identified from the unsupervised data. The cluster analysis is concerned about estimating the number of classes and assigning each observation to a certain class. In this article we discuss a method for clustering via the Laplacian matrix. Also, based on a similar argument, w...

Learning rich visual representations often require training on datasets of millions of manually annotated examples. This substantially limits the scalability of learning effective representations as labeled data is expensive or scarce. In this paper, we address the problem of unsupervised visual representation learning from a large, unlabeled collection of images. By representing each image as ...

This paper addresses the problem of unsupervised feature learning for text data. Our method is grounded in the principle of minimum description length and uses a dictionary-based compression scheme to extract a succinct feature set. Specifically, our method finds a set of word k-grams that minimizes the cost of reconstructing the text losslessly. We formulate document compression as a binary op...

Modeling hypernymy, such as poodle is-a dog, is an important generalization aid to many NLP tasks, such as entailment, relation extraction, and question answering. Supervised learning from labeled hypernym sources, such as WordNet, limit the coverage of these models, which can be addressed by learning hypernyms from unlabeled text. Existing unsupervised methods either do not scale to large voca...

RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...