Representation and learning of visual information for pose recognition

Recovering position from sensor information is an important problem in mobile robotics, known as localisation. Localisation requires a map or some other description of the environment to provide the robot with a context to interpret sensor data. The mobile robot system under discussion is using an artificial neural representation of position. Building a geometrical map of the environment with a single camera and artificial neural networks is difficult. Instead it would be simpler to learn position as a function of the visual input. Usually when learning images, an intermediate representation is employed. An appropriate starting point for biologically plausible image representation is the complex cells of the visual cortex, which have invariance properties that appear useful for localisation. The effectiveness for localisation of two different complex cell models are evaluated. Finally the ability of a simple neural network with single shot learning to recognise these representations and localise a robot is examined.

Adaptive back-propagation in on-line learning of multilayer networks

An adaptive back-propagation algorithm is studied and compared with gradient descent (standard back-propagation) for on-line learning in two-layer neural networks with an arbitrary number of hidden units. Within a statistical mechanics framework, both numerical studies and a rigorous analysis show that the adaptive back-propagation method results in faster training by breaking the symmetry between hidden units more efficiently and by providing faster convergence to optimal generalization than gradient descent.

Finite-size effects in on-line learning of multilayer neural networks

We complement recent advances in thermodynamic limit analyses of mean on-line gradient descent learning dynamics in multi-layer networks by calculating fluctuations possessed by finite dimensional systems. Fluctuations from the mean dynamics are largest at the onset of specialisation as student hidden unit weight vectors begin to imitate specific teacher vectors, increasing with the degree of symmetry of the initial conditions. In light of this, we include a term to stimulate asymmetry in the learning process, which typically also leads to a significant decrease in training time.

The role of biases in on-line learning of two-layer networks

The influence of biases on the learning dynamics of a two-layer neural network, a normalized soft-committee machine, is studied for on-line gradient descent learning. Within a statistical mechanics framework, numerical studies show that the inclusion of adjustable biases dramatically alters the learning dynamics found previously. The symmetric phase which has often been predominant in the original model all but disappears for a non-degenerate bias task. The extended model furthermore exhibits a much richer dynamical behavior, e.g. attractive suboptimal symmetric phases even for realizable cases and noiseless data.

On-line learning of unrealizable tasks

The dynamics of on-line learning is investigated for structurally unrealizable tasks in the context of two-layer neural networks with an arbitrary number of hidden neurons. Within a statistical mechanics framework, a closed set of differential equations describing the learning dynamics can be derived, for the general case of unrealizable isotropic tasks. In the asymptotic regime one can solve the dynamics analytically in the limit of large number of hidden neurons, providing an analytical expression for the residual generalization error, the optimal and critical asymptotic training parameters, and the corresponding prefactor of the generalization error decay.

Semi-supervised learning of hierarchical latent trait models for data visualisation

An interactive hierarchical Generative Topographic Mapping (HGTM) ¸iteH_GTM has been developed to visualise complex data sets. In this paper, we build a more general visualisation system by extending the HGTM visualisation system in 3 directions: bf (1) We generalize HGTM to noise models from the exponential family of distributions. The basic building block is the Latent Trait Model (LTM) developed in ¸iteKaban_pami. bf (2) We give the user a choice of initializing the child plots of the current plot in either em interactive, or em automatic mode. In the interactive mode the user interactively selects ``regions of interest'' as in ¸iteH_GTM, whereas in the automatic mode an unsupervised minimum message length (MML)-driven construction of a mixture of LTMs is employed. bf (3) We derive general formulas for magnification factors in latent trait models. Magnification factors are a useful tool to improve our understanding of the visualisation plots, since they can highlight the boundaries between data clusters. The unsupervised construction is particularly useful when high-level plots are covered with dense clusters of highly overlapping data projections, making it difficult to use the interactive mode. Such a situation often arises when visualizing large data sets. We illustrate our approach on a toy example and apply our system to three more complex real data sets.

An action research study with low proficiency learners in Japan to promote the learning of vocabulary through collocations.

This action research (AR) study explores an alternative approach to vocabulary instruction for low-proficiency university students: a change from targeting individual words from the general service list (West, 1953) to targeting frequent verb + noun collocations. A review of the literature indicated a focus on collocations instead of individual words could potentially address the students’ productive challenges with targeted vocabulary. Over the course of four reflective cycles, this thesis addresses three main aspects of collocation instruction. First, it examines if the students believe studying collocations is more useful than studying individual lexical items. Second, the thesis investigates whether a focus on collocations will lead to improvements in spoken fluency. This is tested through a comparison of a pre-intervention spoken assessment task with the findings from the same task completed 15 weeks later, after the intervention. Third, the thesis explores different procedures for the instructing of collocations under the classroom constraints of a university teaching context. In the first of the four reflective cycles, data is collected which indicates that the students believe a focus on collocations is superior to only teaching individual lexical items, that in the students’ opinion their productive abilities with the targeted structures has improved, and that delexicalized verb collocations are problematic for low-proficiency students. Reflective cycle two produces evidence indicating that productive tasks are superior to receptive tasks for fluency development. In reflective cycle three, productively challenging classroom tasks are investigated further and the findings indicate that tasks with higher productive demands result in greater improvements in spoken fluency. The fourth reflective cycle uses a different type of collocation list: frequent adjective + noun collocations. Despite this change, the findings remain consistent in that certain types of collocations are problematic for low-proficiency language learners and that the evidence shows productive tasks are necessary to improve the students’ spoken ability.

Using computer concordancing for the learning of French as a second language

DUE TO COPYRIGHT RESTRICTIONS ONLY AVAILABLE FOR CONSULTATION AT ASTON UNIVERSITY LIBRARY AND INFORMATION SERVICES WITH PRIOR ARRANGEMENT

Semisupervised learning of hierarchical latent trait models for data visualization

Recently, we have developed the hierarchical Generative Topographic Mapping (HGTM), an interactive method for visualization of large high-dimensional real-valued data sets. In this paper, we propose a more general visualization system by extending HGTM in three ways, which allows the user to visualize a wider range of data sets and better support the model development process. 1) We integrate HGTM with noise models from the exponential family of distributions. The basic building block is the Latent Trait Model (LTM). This enables us to visualize data of inherently discrete nature, e.g., collections of documents, in a hierarchical manner. 2) We give the user a choice of initializing the child plots of the current plot in either interactive, or automatic mode. In the interactive mode, the user selects "regions of interest," whereas in the automatic mode, an unsupervised minimum message length (MML)-inspired construction of a mixture of LTMs is employed. The unsupervised construction is particularly useful when high-level plots are covered with dense clusters of highly overlapping data projections, making it difficult to use the interactive mode. Such a situation often arises when visualizing large data sets. 3) We derive general formulas for magnification factors in latent trait models. Magnification factors are a useful tool to improve our understanding of the visualization plots, since they can highlight the boundaries between data clusters. We illustrate our approach on a toy example and evaluate it on three more complex real data sets. © 2005 IEEE.

Semi-supervised learning of statistical models for natural language understanding

Natural language understanding is to specify a computational model that maps sentences to their semantic mean representation. In this paper, we propose a novel framework to train the statistical models without using expensive fully annotated data. In particular, the input of our framework is a set of sentences labeled with abstract semantic annotations. These annotations encode the underlying embedded semantic structural relations without explicit word/semantic tag alignment. The proposed framework can automatically induce derivation rules that map sentences to their semantic meaning representations. The learning framework is applied on two statistical models, the conditional random fields (CRFs) and the hidden Markov support vector machines (HM-SVMs). Our experimental results on the DARPA communicator data show that both CRFs and HM-SVMs outperform the baseline approach, previously proposed hidden vector state (HVS) model which is also trained on abstract semantic annotations. In addition, the proposed framework shows superior performance than two other baseline approaches, a hybrid framework combining HVS and HM-SVMs and discriminative training of HVS, with a relative error reduction rate of about 25% and 15% being achieved in F-measure.

Supervised learning of graph structure

Graph-based representations have been used with considerable success in computer vision in the abstraction and recognition of object shape and scene structure. Despite this, the methodology available for learning structural representations from sets of training examples is relatively limited. In this paper we take a simple yet effective Bayesian approach to attributed graph learning. We present a naïve node-observation model, where we make the important assumption that the observation of each node and each edge is independent of the others, then we propose an EM-like approach to learn a mixture of these models and a Minimum Message Length criterion for components selection. Moreover, in order to avoid the bias that could arise with a single estimation of the node correspondences, we decide to estimate the sampling probability over all the possible matches. Finally we show the utility of the proposed approach on popular computer vision tasks such as 2D and 3D shape recognition. © 2011 Springer-Verlag.

Effects of real -time captioning and sign language interpreting on the learning of college students who are deaf or hard of hearing

College personnel are required to provide accommodations for students who are deaf and hard of hearing (D/HoH), but few empirical studies have been conducted on D/HoH students as they learn under the various accommodation conditions (sign language interpreting, SLI, real-time captioning, RTC, and both). Guided by the experiences of students who are D/HoH at Miami-Dade College (MDC) who requested RTC in addition to SLI as accommodations, the researcher adopted Merten’s transformative-emancipatory theoretical framework that values perceptions and voice of students who are D/HoH. A mixed methods design addressed two research questions: Did student learning differ for each accommodation? What did students experience while learning through accommodations? Participants included 30 students who were D/HoH (60% women). They represented MDC’s majority minority population: 10% White (non-Hispanic), 20% Black (non-Hispanic, including Haitian/Caribbean), 67% Hispanic, and 3% other. Hearing loss, ranged from severe-profound (70%) to mild-moderate (30%). All were able to communicate with American Sign Language: Learning was measured while students who were D/HoH viewed three lectures under three accommodation conditions (SLI, RTC, SLI+RTC). The learning measure was defined as the difference in pre- and post-test scores on tests of the content presented in the lectures. Using repeated measure ANOVA and ANCOVA, confounding variables of fluency in American Sign Language and literacy skills were treated as covariates. Perceptions were obtained through interviews and verbal protocol analysis that were signed, videotaped, transcribed, coded, and examined for common themes and metacognitive strategies. No statistically significant differences were found among the three accommodations on the learning measure. Students who were D/HoH expressed thoughts about five different aspects of their learning while they viewed lectures: (a) comprehending the information, (b) feeling a part of the classroom environment, (c) past experiences with an accommodation, (d) individual preferences for an accommodation, (e) suggestions for improving an accommodation. They exhibited three metacognitive strategies: (a) constructing knowledge, (b) monitoring comprehension, and (c) evaluating information. No patterns were found in the types of metacognitive strategies used for any particular accommodation. The researcher offers recommendations for flexible applications of the standard accommodations used with students who are D/HoH.