This is an abbreviated revision of the University of Waterloo research report CORR 94-32. y

In this paper, several vision-based robot control methods are classified following an analogy with well known minimization methods. Comparing the rate of convergence between minimization algorithms helps us to understand the difference of performance of the control schemes. In particular, it is shown that standard vision-based control methods have in general low rates of convergence. Thus, the performance of vision-based control could be improved using schemes which perform like the Newton minimization algorithm that has a high convergence rate. Unfortunately, the Newton minimization method needs the computation of second derivatives that can be ill-conditioned causing convergence problems. In order to solve these problems, this paper proposes two new control schemes based on efficient second-order minimization techniques.

We apply the zero-one integer programming algorithm described in Karmarkar [12] and Karmarkar, Resende and Ramakrishnan [13] to solve randomly generated instances of the satisfiability problem (SAT). The interior point algorithm is briefly reviewed and shown to be easily adapted to solve large instances of SAT. Hundreds of instances of SAT (having from 100 to 1000 variables and 100 to 32,000 clauses) are randomly generated and solved. For comparison, we attempt to solve the problems via linear programming relaxation with MINOS.

Abstract — We describe theoretical and experimental results for the extrinsic calibration of sensor platform consisting of a camera and a 2D laser range finder. The calibration is based on observing a planar checkerboard pattern and solving for constraints between the “views ” of a planar checkerboard calibration pattern from a camera and laser range finder. we give a direct solution that minimizes an algebraic error from this constraint, and subsequent nonlinear refinement minimizes a re-projection error. To our knowledge, this is the first published calibration tool for this problem. Additionally we show how this constraint can reduce the variance in estimating intrinsic camera parameters. I.

Abstract not found

This paper presents new methods for training large neural networks for phoneme probability estimation. An architecture combining time-delay windows and recurrent connections is used to capture the important dynamic information of the speech signal. Because the number of connections in a fully connected recurrent network grows super-linear with the number of hidden units, schemes for sparse connection and connection pruning are explored. It is found that sparsely connected networks outperform their fully connected counterparts with an equal number of connections. The implementation of the combined architecture and training scheme is described in detail. The networks are evaluated in a hybrid HMM/ANN system for phoneme recognition on the TIMIT database, and for word recognition on the WAXHOLM database. The achieved phone error-rate, 27.8%, for the standard 39 phoneme set on the core test-set of the TIMIT database is in the range of the lowest reported. All training and simulation softwar...

When human raters are presented with a collection of shapes and asked to rank them according to their aesthetic appeal, the results often indicate that there is a statistical consensus among the raters. Yet it might be difficult to define a succinct set of rules that capture the aesthetic preferences of the raters. In this work, we explore a data-driven approach to aesthetic enhancement of such shapes. Specifically, we focus on the challenging problem of enhancing the aesthetic appeal (or the attractiveness) of human faces in frontal photographs (portraits), while maintaining close similarity with the original. The key component in our approach is an automatic facial attractiveness engine trained on datasets of faces with accompanying facial attractiveness ratings collected from groups of human raters. Given a new face, we extract a set of distances between a variety of facial feature locations, which define a point in a high-dimensional “face space”. We then search the face space for a nearby point with a higher predicted attractiveness rating. Once such a point is found, the corresponding facial distances are embedded in the plane and serve as a target to define a 2D warp field which maps the original facial features to their adjusted locations. The effectiveness of our technique was experimentally validated by independent rating experiments, which indicate that it is indeed capable of increasing the facial attractiveness of most portraits that we have experimented with. Keywords: warping 1

Research on using interior point algorithms to solve combinatorial optimization and integer programming problems is surveyed. This paper discusses branch and cut methods for integer programming problems, a potential reduction method based on transforming an integer programming problem to an equivalent nonconvex quadratic programming problem, interior point methods for solving network flow problems, and methods for solving multicommodity flow problems, including an interior point column generation algorithm.

We use Stem-ML to build an automatic learning system for Mandarin prosody that allows us to make quantitative measurements of prosodic strengths. Stem-ML is a phenomenological model of the muscle dynamics and planning process that controls the tension of the vocal folds. Because Stem-ML describes the interactions between nearby tones or accents, we were able to use a highly constrained model with only one accent template for each lexical tone category, and a single prosodic strength per word. The model accurately reproduces the intonation of the speaker, capturing 87 % of the variance of. The result reveals strong alternating metrical patterns in words, and shows that the speaker uses word strength to mark a hierarchy of boundaries. 1.

We review the Space Mapping (SM) concept and its applications in engineering optimization and modeling. The aim of SM is to avoid computationally expensive calculations encountered in simulating an engineering system. The existence of less accurate but fast physically-based models is exploited. SM drives the optimization iterates of the time-intensive model using the fast model. Several algorithms have been developed for SM optimization, including the original SM algorithm, Aggressive Space Mapping (ASM), Trust Region Aggressive Space Mapping (TRASM) and Hybrid Aggressive Space Mapping (HASM). An essential subproblem of any SM based optimization algorithm is parameter extraction. The uniqueness of this optimization subproblem has been crucial to the success of SM optimization. Different approaches to enhance the uniqueness are reviewed. We also discuss new developments in Space Mapping-based Modeling (SMM). These include Space Derivative Mapping (SDM), Generalized Space Mapping (GSM) and Space Mapping-based Neuromodeling (SMN). Finally, we address open points for research and future development.