We explore the training of deep neural networks to produce vector representations using weakly labelled information in the form of binary similarity labels for pairs of training images. Previous methods such as siamese networks, IMAX and others, have used fixed cost functions such as $L_1$, $L_2$-norms and mutual information to drive the representations of similar images together and different images apart. In this work, we formulate learning as maximizing the likelihood of binary similarity labels for pairs of input images, under a parameterized probabilistic similarity model. We describe and evaluate several forms of the similarity model that account for false positives and false negatives differently. We extract representations of MNIST, AT\&T ORL and COIL-100 images and use them to obtain classification results. We compare these results with state-of-the-art techniques such as deep neural networks and convolutional neural networks. We also study our method from a dimensionality reduction prospective.

No description available.

AdaBoost has been considered one of the best classifiers ever developed, but two important problems have not yet been addressed. The first is the dependency on the ``weak" learner, and the second is the failure to maintain the performance of learners with small error rates (i.e. ``strong" learners). To solve the first problem, this work proposes using a different learner in each iteration - known as AdaBoost Dynamic (AD) - thereby ensuring that the performance of the algorithm is almost equal to that of the best ``weak" learner executed with AdaBoost.M1. The work then further modifies the procedure to vary the learner in each iteration, in order to locate the learner with the smallest error rate in its training data. This is done using the same weight calculation as in the original AdaBoost; this version is known as AdaBoost Dynamic with Exponential Loss (AB-EL). The results were poor, because AdaBoost does not perform well with strong learners, so, in this sense, the work confirmed previous works' results. To determine how to improve the performance, the weight calculation is modified to use the sigmoid function with algorithm output being the derivative of the same sigmoid function, rather than the logistic regression weight calculation originally used by AdaBoost; this version is known as AdaBoost Dynamic with Logistic Loss (AB-DL). This work presents the convergence proof that binomial weight calculation works, and that this approach improves the results for the strong learner, both theoretically and empirically. AB-DL also has some disadvantages, like the search for the ``best" classifier and that this search reduces the diversity among the classifiers. In order to attack these issues, another algorithm is proposed that combines AD ``weak" leaner execution policy with a small modification of AB-DL's weight calculation, called AdaBoost Dynamic with Added Cost (AD-AC). AD-AC also has a theoretical upper bound error, and the algorithm offers a small accuracy improvement when compared with AB-DL, and traditional AdaBoost approaches. Lastly, this work also adapts AD-AC's weight calculation approach to deal with data stream problem, where classifiers must deal with very large data sets (in the order of millions of instances), and limited memory availability.

No description available.

No description available.

No description available.

No description available.

Email has become a part of most people's lives, and the ever increasing amount of messages people receive can lead to email overload. We attempt to mitigate this problem using email thread summarization. Summaries can be used for things other than just replacing an incoming email message. They can be used in the business world as a form of corporate memory, or to allow a new team member an easy way to catch up on an ongoing conversation. Email threads are of particular interest to summarization because they contain much structural redundancy due to their conversational nature. Our email thread summarization approach uses machine learning to pick which sentences from the email thread to use in the summary. A machine learning summarizer must be trained using previously labeled data, i.e. manually created summaries. After being trained our summarization algorithm can generate summaries that on average contain over 70% of the same sentences as human annotators. We show that labeling some key features such as speech acts, meta sentences, and subjectivity can improve performance to over 80% weighted recall. To create such email summarization software, an email dataset is needed for training and evaluation. Since email communication is a private matter, it is hard to get access to real emails for research. Furthermore these emails must be annotated with human generated summaries as well. As these annotated datasets are rare, we have created one and made it publicly available. The BC3 corpus contains annotations for 40 email threads which include extractive summaries, abstractive summaries with links, and labeled speech acts, meta sentences, and subjective sentences. While previous research has shown that machine learning algorithms are a promising approach to email summarization, there has not been a study on the impact of the choice of algorithm. We explore new techniques in email thread summarization using several different kinds of regression, and the results show that the choice of classifier is very critical. We also present a novel feature set for email summarization and do analysis on two email corpora: the BC3 corpus and the Enron corpus.

No description available.

Thesis (Ph.D.)--University of Melbourne, Dept. of Electrical and Electronic Engineering, 2006. / Typescript. Includes bibliographical references (leaves 231-238).