Speech intensity is one of the main prosodic cues, playing a role in most of the suprasegmental phenomena. Despite this, its contribution to the signalling of prosodic hierarchy is still relatively understudied, compared to the other cues, like duration or fundamental frequency. We present here an investigation on the role of intensity in prosodic boundary detection in four different languages,...

Unsupervised neural network learning extracts hidden features from unlabeled training data. This is used as a pretraining step for further supervised learning in deep networks. Hence, understanding unsupervised learning is of fundamental importance. Here, we study the unsupervised learning from a finite number of data, based on the restricted Boltzmann machine where only one hidden neuron is co...

This paper presents a comparative account of unsupervised and supervised learning models and their pattern classification evaluations as applied to the higher education scenario. Classification plays a vital role in machine based learning algorithms and in the present study, we found that, though the error back-propagation learning algorithm as provided by supervised learning model is very effi...

Recently, multilayer bootstrap network (MBN) has demonstrated promising performance in unsupervised dimensionality reduction. It can learn compact representations in standard data sets, i.e. MNIST and RCV1. However, as a bootstrap method, the prediction complexity of MBN is high. In this paper, we propose an unsupervised model compression framework for this general problem of unsupervised boots...

With lot of research and advancement of deep learning, complex unsupervised learning is applied for extracting deep hierarchies of features especially to images. But, off-the-shelf unsupervised learning algorithms combined with deep learning techniques would yield results similar to complext,time consuming Deep learning algorithms. In this report, I would use K-means algorithm based on [1][3] a...

xviii

We exhibit a duality between two perceptrons which allows us to compare the theoretical analysis of supervised and unsupervised learning tasks. The rst perceptron has one output and is asked to learn a classiication of p patterns. The second (dual) perceptron has p outputs and is asked to transmit as much information as possible on a distribution of inputs. We show in particular that the maximu...

In the paper we analyze 26 communities across the United States with the objective to understand what attaches people to their community and how this attachment differs among communities. How different are attached people from unattached? What attaches people to their community? How different are the communities? What are key drivers behind emotional attachment? To address these questions, grap...