Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

Automatic Labeling of Software Components and their Evolution using Log-Likelihood Ratio of Word Frequencies in Source Code

As more and more open-source software components become available on the internet we need automatic ways to label and compare them. For example, a developer who searches for reusable software must be able to quickly gain an understanding of retrieved components. This understanding cannot be gained at the level of source code due to the semantic gap between source code and the domain model. In this paper we present a lexical approach that uses the log-likelihood ratios of word frequencies to automatically provide labels for software components. We present a prototype implementation of our labeling/comparison algorithm and provide examples of its application. In particular, we apply the approach to detect trends in the evolution of a software system.

Dutch boundaries

In many schools of architecture the 1970s have been an important watershed for the way in which architecture was taught. For example, recent studies have stressed the importance of Aldo Rossi for the changes in the teaching of architec-ture at the ETH in Zürich that before was based on orthodox modern principles. A similar struggle between an orthodox conception of modernity and its criticism took place at the architectural faculty of Delft, in the Netherlands. Although Delft is an important European school of architecture, the theoretical work produced during this period is not largely known outside the Netherlands. This is perhaps due to the fact that most studies were published in Dutch. With this article, I intend to make the architectural theory developed during this period known to a larger public. The article describes the intellectual journey made by Dutch stu-dents of architecture in the 1970s and 1980s. This was the quest to receive recognition for the intellectual substance of architecture: the insight architecture could be a discourse and a form of knowledge and not only a method of building. Specifically, the work of the architectural theoretician Wim Nijenhuis is highlight-ed. However, as I point out in this article, the results of this journey also had its problematic sides. This becomes clear from the following sentence taken from the dissertation of Wim Nijenhuis: "The search for metaphysical fiction and the tendency towards a technological informed absolute through fully transparent and simultaneous information, should be contested by a fantasy dimension, that does not wish to 'overcome' a given situation and that does not rely on 'creativi-ty' (that would still be historical and humanistic)." Texts like this have a hermet-ic quality that is not easy to comprehend for an architectural public. Even more, there is an important debate looming behind these sentences. As an important outcome of their quest the architectural students in Delft asked themselves: how do we give form to architectural theory once its claim to truth is exposed as an illusion? For Nijenhuis, the discourse about architecture is a mere 'artful game with words': a fiction, besides other forms of fiction like poetry or literature. The question is then if we have not entered the realm of total subjectivity and relativ-ism with this position. From what can the discourse of architecture derive its authority after the death of God?

Recognition memory across the lifespan: the impact of word frequency and study-test interval on estimates of familiarity and recollection

The goal of this study was to investigate recognition memory performance across the lifespan and to determine how estimates of recollection and familiarity contribute to performance. In each of three experiments, participants from five groups from 14 up to 85 years of age (children, young adults, middle-aged adults, young-old adults, and old-old adults) were presented with high- and low-frequency words in a study phase and were tested immediately afterwards and/or after a one day retention interval. The results showed that word frequency and retention interval affected recognition memory performance as well as estimates of recollection and familiarity. Across the lifespan, the trajectory of recognition memory followed an inverse u-shape function that was neither affected by word frequency nor by retention interval. The trajectory of estimates of recollection also followed an inverse u-shape function, and was especially pronounced for low-frequency words. In contrast, estimates of familiarity did not differ across the lifespan. The results indicate that age differences in recognition memory are mainly due to differences in processes related to recollection while the contribution of familiarity-based processes seems to be age-invariant.

Unconscious word stem completion priming in a mirror-masking paradigm

The aim of this study was to investigate unconscious priming by the use of a spatial mirror-masking paradigm. Words and nonwords with no under-length letters are mirrored at their horizontal axis. The results are figures of geometric-like forms that contain letters in their upper part. In the three experiments reported in this study, a priming procedure used such mirrored words and nonwords as primes. Participants were ignorant of the nature of the construction of the stimuli. Perceptual reports of the participants revealed that they did not realize that words were hidden in the primes. Nevertheless, they showed priming in all three experiments. Priming effects were replicated with prime–target SOAs of between 1 and 3 s. Functional dissociations were found between ignorant and informed participants. Informed groups showed perceptual and semantic priming, while ignorant groups showed only perceptual priming.