Data fusion and matching by maximizing statistical dependencies

The core aim of machine learning is to make a computer program learn from the experience. Learning from data is usually defined as a task of learning regularities or patterns in data in order to extract useful information, or to learn the underlying concept. An important sub-field of machine learning is called multi-view learning where the task is to learn from multiple data sets or views describing the same underlying concept. A typical example of such scenario would be to study a biological concept using several biological measurements like gene expression, protein expression and metabolic profiles, or to classify web pages based on their content and the contents of their hyperlinks. In this thesis, novel problem formulations and methods for multi-view learning are presented. The contributions include a linear data fusion approach during exploratory data analysis, a new measure to evaluate different kinds of representations for textual data, and an extension of multi-view learning for novel scenarios where the correspondence of samples in the different views or data sets is not known in advance. In order to infer the one-to-one correspondence of samples between two views, a novel concept of multi-view matching is proposed. The matching algorithm is completely data-driven and is demonstrated in several applications such as matching of metabolites between humans and mice, and matching of sentences between documents in two languages.

Robot navigation in dense crowds : statistical models and experimental studies of human robot cooperation

This thesis explores the problem of mobile robot navigation in dense human crowds. We begin by considering a fundamental impediment to classical motion planning algorithms called the freezing robot problem: once the environment surpasses a certain level of complexity, the planner decides that all forward paths are unsafe, and the robot freezes in place (or performs unnecessary maneuvers) to avoid collisions. Since a feasible path typically exists, this behavior is suboptimal. Existing approaches have focused on reducing predictive uncertainty by employing higher fidelity individual dynamics models or heuristically limiting the individual predictive covariance to prevent overcautious navigation. We demonstrate that both the individual prediction and the individual predictive uncertainty have little to do with this undesirable navigation behavior. Additionally, we provide evidence that dynamic agents are able to navigate in dense crowds by engaging in joint collision avoidance, cooperatively making room to create feasible trajectories. We accordingly develop interacting Gaussian processes, a prediction density that captures cooperative collision avoidance, and a "multiple goal" extension that models the goal driven nature of human decision making. Navigation naturally emerges as a statistic of this distribution.

Most importantly, we empirically validate our models in the Chandler dining hall at Caltech during peak hours, and in the process, carry out the first extensive quantitative study of robot navigation in dense human crowds (collecting data on 488 runs). The multiple goal interacting Gaussian processes algorithm performs comparably with human teleoperators in crowd densities nearing 1 person/m², while a state of the art noncooperative planner exhibits unsafe behavior more than 3 times as often as the multiple goal extension, and twice as often as the basic interacting Gaussian process approach. Furthermore, a reactive planner based on the widely used dynamic window approach proves insufficient for crowd densities above 0.55 people/m². We also show that our noncooperative planner or our reactive planner capture the salient characteristics of nearly any dynamic navigation algorithm. For inclusive validation purposes, we show that either our non-interacting planner or our reactive planner captures the salient characteristics of nearly any existing dynamic navigation algorithm. Based on these experimental results and theoretical observations, we conclude that a cooperation model is critical for safe and efficient robot navigation in dense human crowds.

Finally, we produce a large database of ground truth pedestrian crowd data. We make this ground truth database publicly available for further scientific study of crowd prediction models, learning from demonstration algorithms, and human robot interaction models in general.

Integrated treatment of first episode psychosis with online training (e-learning): study protocol for a randomised controlled trial

Background: The integrated treatment of first episode psychosis has been shown to improve functionality and negative symptoms in previous studies. In this paper, we describe a study of integrated treatment (individual psychoeducation complementary to pharmacotherapy) versus treatment as usual, comparing results at baseline with those at 6-month re-assessment (at the end of the study) for these patients, and online training of professionals to provide this complementary treatment, with the following objectives: 1) to compare the efficacy of individual psychoeducation as add-on treatment versus treatment as usual in improving psychotic and mood symptoms; 2) to compare adherence to medication, functioning, insight, social response, quality of life, and brain-derived neurotrophic factor, between both groups; and 3) to analyse the efficacy of online training of psychotherapists. Methods/design: This is a single-blind randomised clinical trial including patients with first episode psychosis from hospitals across Spain, randomly assigned to either a control group with pharmacotherapy and regular sessions with their psychiatrist (treatment as usual) or an intervention group with integrated care including treatment as usual plus a psychoeducational intervention (14 sessions). Training for professionals involved at each participating centre was provided by the coordinating centre (University Hospital of Alava) through video conferences. Patients are evaluated with an extensive battery of tests assessing clinical and sociodemographic characteristics (Positive and Negative Syndrome Scale, State-Trait Anxiety Inventory, Liebowitz Social Anxiety Scale, Hamilton Rating Scale for Depression, Scale to Assess Unawareness of Mental Disorders, Strauss and Carpenter Prognostic Scale, Global Assessment of Functioning Scale, Morisky Green Adherence Scale, Functioning Assessment Short Test, World Health Organization Quality of Life instrument WHOQOL-BREF (an abbreviated version of the WHOQOL-100), and EuroQoL questionnaire), and brain-derived neurotrophic factor levels are measured in peripheral blood at baseline and at 6 months. The statistical analysis, including bivariate analysis, linear and logistic regression models, will be performed using SPSS. Discussion: This is an innovative study that includes the assessment of an integrated intervention for patients with first episode psychosis provided by professionals who are trained online, potentially making it possible to offer the intervention to more patients.

Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs

This article presents a novel algorithm for learning parameters in statistical dialogue systems which are modeled as Partially Observable Markov Decision Processes (POMDPs). The three main components of a POMDP dialogue manager are a dialogue model representing dialogue state information; a policy that selects the system's responses based on the inferred state; and a reward function that specifies the desired behavior of the system. Ideally both the model parameters and the policy would be designed to maximize the cumulative reward. However, while there are many techniques available for learning the optimal policy, no good ways of learning the optimal model parameters that scale to real-world dialogue systems have been found yet. The presented algorithm, called the Natural Actor and Belief Critic (NABC), is a policy gradient method that offers a solution to this problem. Based on observed rewards, the algorithm estimates the natural gradient of the expected cumulative reward. The resulting gradient is then used to adapt both the prior distribution of the dialogue model parameters and the policy parameters. In addition, the article presents a variant of the NABC algorithm, called the Natural Belief Critic (NBC), which assumes that the policy is fixed and only the model parameters need to be estimated. The algorithms are evaluated on a spoken dialogue system in the tourist information domain. The experiments show that model parameters estimated to maximize the expected cumulative reward result in significantly improved performance compared to the baseline hand-crafted model parameters. The algorithms are also compared to optimization techniques using plain gradients and state-of-the-art random search algorithms. In all cases, the algorithms based on the natural gradient work significantly better. © 2011 ACM.

Statistical inference for single- and multi-band probabilistic amplitude demodulation.

Amplitude demodulation is an ill-posed problem and so it is natural to treat it from a Bayesian viewpoint, inferring the most likely carrier and envelope under probabilistic constraints. One such treatment is Probabilistic Amplitude Demodulation (PAD), which, whilst computationally more intensive than traditional approaches, offers several advantages. Here we provide methods for estimating the uncertainty in the PAD-derived envelopes and carriers, and for learning free-parameters like the time-scale of the envelope. We show how the probabilistic approach can naturally handle noisy and missing data. Finally, we indicate how to extend the model to signals which contain multiple modulators and carriers.

Learning based automatic face annotation for arbitrary poses and expressions from frontal images only

Statistical approaches for building non-rigid deformable models, such as the Active Appearance Model (AAM), have enjoyed great popularity in recent years, but typically require tedious manual annotation of training images. In this paper, a learning based approach for the automatic annotation of visually deformable objects from a single annotated frontal image is presented and demonstrated on the example of automatically annotating face images that can be used for building AAMs for fitting and tracking. This approach employs the idea of initially learning the correspondences between landmarks in a frontal image and a set of training images with a face in arbitrary poses. Using this learner, virtual images of unseen faces at any arbitrary pose for which the learner was trained can be reconstructed by predicting the new landmark locations and warping the texture from the frontal image. View-based AAMs are then built from the virtual images and used for automatically annotating unseen images, including images of different facial expressions, at any random pose within the maximum range spanned by the virtually reconstructed images. The approach is experimentally validated by automatically annotating face images from three different databases. © 2009 IEEE.

Active learning of model evidence using Bayesian quadrature

Numerical integration is a key component of many problems in scientific computing, statistical modelling, and machine learning. Bayesian Quadrature is a modelbased method for numerical integration which, relative to standard Monte Carlo methods, offers increased sample efficiency and a more robust estimate of the uncertainty in the estimated integral. We propose a novel Bayesian Quadrature approach for numerical integration when the integrand is non-negative, such as the case of computing the marginal likelihood, predictive distribution, or normalising constant of a probabilistic model. Our approach approximately marginalises the quadrature model's hyperparameters in closed form, and introduces an active learning scheme to optimally select function evaluations, as opposed to using Monte Carlo samples. We demonstrate our method on both a number of synthetic benchmarks and a real scientific problem from astronomy.

Bayesian Learning of Noisy Markov Decision Processes

We consider the inverse reinforcement learning problem, that is, the problem of learning from, and then predicting or mimicking a controller based on state/action data. We propose a statistical model for such data, derived from the structure of a Markov decision process. Adopting a Bayesian approach to inference, we show how latent variables of the model can be estimated, and how predictions about actions can be made, in a unified framework. A new Markov chain Monte Carlo (MCMC) sampler is devised for simulation from the posterior distribution. This step includes a parameter expansion step, which is shown to be essential for good convergence properties of the MCMC sampler. As an illustration, the method is applied to learning a human controller.

Statistical Evaluation of the Predictive Toxicology Challenge 2000-2001

Toivonen, H., Srinivasan, A., King, R. D., Kramer, S. and Helma, C. (2003) Statistical Evaluation of the Predictive Toxicology Challenge 2000-2001. Bioinformatics 19: 1183-1193

An active learning approach for rapid characterization of endothelial cells in human tumors.

Currently, no available pathological or molecular measures of tumor angiogenesis predict response to antiangiogenic therapies used in clinical practice. Recognizing that tumor endothelial cells (EC) and EC activation and survival signaling are the direct targets of these therapies, we sought to develop an automated platform for quantifying activity of critical signaling pathways and other biological events in EC of patient tumors by histopathology. Computer image analysis of EC in highly heterogeneous human tumors by a statistical classifier trained using examples selected by human experts performed poorly due to subjectivity and selection bias. We hypothesized that the analysis can be optimized by a more active process to aid experts in identifying informative training examples. To test this hypothesis, we incorporated a novel active learning (AL) algorithm into FARSIGHT image analysis software that aids the expert by seeking out informative examples for the operator to label. The resulting FARSIGHT-AL system identified EC with specificity and sensitivity consistently greater than 0.9 and outperformed traditional supervised classification algorithms. The system modeled individual operator preferences and generated reproducible results. Using the results of EC classification, we also quantified proliferation (Ki67) and activity in important signal transduction pathways (MAP kinase, STAT3) in immunostained human clear cell renal cell carcinoma and other tumors. FARSIGHT-AL enables characterization of EC in conventionally preserved human tumors in a more automated process suitable for testing and validating in clinical trials. The results of our study support a unique opportunity for quantifying angiogenesis in a manner that can now be tested for its ability to identify novel predictive and response biomarkers.

Memorability as a measure of processing: a unit analysis of prose and list learning.

The percentage of subjects recalling each unit in a list or prose passage is considered as a dependent measure. When the same units are recalled in different tasks, processing is assumed to be the same; when different units are recalled, processing is assumed to be different. Two collections of memory tasks are presented, one for lists and one for prose. The relations found in these two collections are supported by an extensive reanalysis of the existing prose memory literature. The same set of words were learned by 13 different groups of subjects under 13 different conditions. Included were intentional free-recall tasks, incidental free recall following lexical decision, and incidental free recall following ratings of orthographic distinctiveness and emotionality. Although the nine free-recall tasks varied widely with regard to the amount of recall, the relative probability of recall for the words was very similar among the tasks. Imagery encoding and recognition produced relative probabilities of recall that were different from each other and from the free-recall tasks. Similar results were obtained with a prose passage. A story was learned by 13 different groups of subjects under 13 different conditions. Eight free-recall tasks, which varied with respect to incidental or intentional learning, retention interval, and the age of the subjects, produced similar relative probabilities of recall, whereas recognition and prompted recall produced relative probabilities of recall that were different from each other and from the free-recall tasks. A review of the prose literature was undertaken to test the generality of these results. Analysis of variance is the most common statistical procedure in this literature. If the relative probability of recall of units varied across conditions, a units by condition interaction would be expected. For the 12 studies that manipulated retention interval, an average of 21% of the variance was accounted for by the main effect of retention interval, 17% by the main effect of units, and only 2% by the retention interval by units interaction. Similarly, for the 12 studies that varied the age of the subjects, 6% of the variance was accounted for by the main effect of age, 32% by the main effect of units, and only 1% by the interaction of age by units.(ABSTRACT TRUNCATED AT 400 WORDS)

Learning from experience

Training courses for researchers are discussed in some detail. The preparation of researchers and of statisticians for consulting sessions, and the opportunities such sessions provide for training, are considered.

The role of Minitab in teaching and learning statistics

This paper describes how the statistical package Minitab is used in teaching statistics in our undergraduate programmes in Mathematics and Statistics to enhance student learning. How the sophisticated recent versions of Minitab can be used to help students understand statistical concepts, develop their statistical thinking and gain valuable skills in performing statistical analysis are discussed.