Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Phd by thesis

Data Mining Practical Machine Learning Tools and Techniques

The power of feedback.

Emotion and Adaptation

In social robotics, user-personalised messages is a technique that can be used to persuade a person to do something. Those messages can be personalised according to the personality of whom will receive this message. So, it is essential to know the personality traits of the target. However, we have many traits, e.g., a person can be extroverted, assertive, logical, among others. Because of that, it is challenging to create a strategy that can reach all the traits. In this sense, we chose to focus our persuasion strategies to approach the assertive trait of a person. The strategies were applied in a storytelling scenario with an autonomous social robot behaving assertively using strategies to suggesting the person change the decision with assertive messages and nonverbal persuasive techniques. Besides, we take into account the assertiveness level of the participant to measure if this level influences the acceptance of robot suggestion or not. We observed from the results that a person’s assertiveness level might influence the perception regarding the persuasive agent and the decisions-made in the task.

The Importance of the Person's Assertiveness in Persuasive Human-Robot Interactions.

synthetic characters which interact with objects in dynamic virtual worlds is important when we want the agents to act in an autonomous and non-preplanned way. Such interactions with objects would allow the synthetic characters to behave in a more believable way. Once objects offer innumerous uses, it is essential that the agent is able to acquire the necessary knowledge to identify action possibilities in the objects while interacting with them. We propose a conceptual framework that allows the agents to identify possible interactions with objects based in past experiences with other objects. Starting from sensory patterns collected during interactions with objects, the agent is able to acquire conceptual knowledge about regularities of the world, its internal states and its own actions. The presented work also proposes that such acquired knowledge may be used by the agent in order to satisfy its needs and goals by interacting with objects. Preliminary tests were made and it is possible to state that our agents are able to acquire valid conceptual knowledge about the regularities in the environment and its objects, its own actions and causal relations between them.

Learning to Interact: Connecting Perception with Action in Virtual Environments (Short Paper)

In recent years, virtual environments have evolved from single user and single agent, to multi-user and multi-agent. Furthermore, with the emergence of synthetic characters, collaborative virtual environments can now be populated with characters and users, all interacting, collaborating or competing between each other. However, the user’s interaction with the synthetic characters is not always the best, and it is only positive if the characters are able to show a coherent and believable behaviour. Therefore, in scenarios where users and synthetic characters interact as a group, it is very important that the interactions follow a believable group dynamics. Focusing on this problem, we have developed a model that supports the dynamics of a group of synthetic characters, inspired by theories of group dynamics developed in human social psychological sciences. The dynamics is driven by a characterization of the different types of interactions that may occur in the group, which are differentiated in two main categories: the socio-emotional interactions and the task related interactions.

A Believable Group in the Synthetic Mind

I'm a Nephrologist and I give urea to my patients. SIAD in oncological patients.

In this short paper, we exploit robotics domain knowledge, be it acquired from humans or self-organization, to alleviate learning and control challenges from directly dealing with raw demonstrations or sparse reward signals. We take a unified latent variable perspective in incorporating domain constraints. The latent variables are regarded as task parameters or representations, which rationalize task observations with a generative model. The constraints can thus be specified with structured latent variables. Different from many related works, we explore latent structures that are computationally feasible and robotics-oriented to facilitate both task learning and control synthesis. The paper will briefly discuss adopted structures ranging from parameter dependency, modality and dynamical associativity, extending imitation learning such as inverse optimal control and deep generative models. The framework is shown to be effective in a range of manipulation tasks, including 1) learning variable impedance controllers in robotic handwriting; 2) boosting motion synthesis for writing novel symbols; 3) reasoning an internal model to score a balltarget under malfunctioning visual input.

Ana Paiva

Papers

The Importance of the Person's Assertiveness in Persuasive Human-Robot Interactions.

Learning to Interact: Connecting Perception with Action in Virtual Environments (Short Paper)

A Believable Group in the Synthetic Mind

I'm a Nephrologist and I give urea to my patients. SIAD in oncological patients.

Boosting Robot Learning and Control with Domain Constraints