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 the past years, research on the embodiment of interactive social agents has been focused on comparisons between robots and virtually-displayed agents. Our work contributes to this line of research by providing a comparison between social robots and disembodied agents exploring the role of embodiment within group interactions. We conducted a user study where participants formed a team with two agents to play a Collective Risk Dilemma (CRD). Besides having two levels of embodiment as between-subjects —physically-embodied and disembodied—, we also manipulated the agents’ degree of cooperation as a within-subjects variable —one of the agents used a prosocial strategy and the other used selfish strategy. Our results show that while trust levels were similar between the two conditions of embodiment, participants identified more with the team of embodied agents. Surprisingly, when the agents were disembodied, the prosocial agent was rated more positively and the selfish agent was rated more negatively, compared to when they were embodied. The obtained results support that embodied interactions might improve how humans relate with agents in team settings. However, if the social aspects can positively mask selfish behaviours, as our results suggest, a dark side of embodiment may emerge.

http://www.roboticsproceedings.org/rss16/p010.pdf

The Dark Side of Embodiment - Teaming Up With Robots VS Disembodied Agents

Autonomous characters in virtual environmentshave the potential to improve the interaction experience of users, specially, their social experience.This effect is driven by the interactions occurring between users and the autonomous characters, that in certain scenarios can be in the context of a group.However, for these group interactions to be successful, it is not enough to assure that the autonomous charactersbehave in a coherent manner from an individual perspective,but it is also necessary that they exhibit behavioursthat are coherent with the group composition, context andstructure. Therefore, we have developed a model to support believable group dynamics of autonomous characters, inspired in theories developed in human social psychological sciences. This model defines the knowledge that eachindividual should build about the others and about the group it belongs, and how this knowledge drives their interactions in the group. The model was integrated in the mind of the autonomous characters that perform a collaborative task, in a computer game, with a human player. The game was used in a study that showed that players' interaction experience was better when interaction with groups that followed our model, namely, regarding trust and social identification with the group. In addition, we found some evidence that players prefer playing in groups that have higher level of conflict.

The user in the group: evaluating the effects of autonomous group dynamics

We study a multiplayer extension of the well-known Ultimatum Game (UG) through the lens of a reinforcement learning algorithm. Multiplayer Ultimatum Game (MUG) allows us to study fair behaviors beyond the traditional pairwise interaction models. Here, a proposal is made to a quorum of Responders, and the overall acceptance depends on reaching a threshold of individual acceptances. We show that learning agents coordinate their behavior into different strategies, depending on factors such as the group acceptance threshold and the group size. Overall, our simulations show that stringent group criteria trigger fairer proposals and the effect of group size on fairness depends on the same group acceptance criteria.

Learning to be Fair in Multiplayer Ultimatum Games: (Extended Abstract)

Computer-assisted psychotherapy represents a major new development in clinical practice and is expected to play an increasingly important role over the next 10 years. Use of computers in therapy ranges from relatively simple communication-support tools, to the use of complex simulations and synthetic agents in virtual reality environments. At the simpler end of this spectrum, computer-mediated communication (CMC) has already entered clinical practice, in the form of internet communication, email and video-conferencing. While clearly important, these technologies are not as potentially revolutionary as the use of synthetic agents and simulated virtual environments. It is these more sophisticated computer technologies that are the primary focus of this panel. The success of existing virtual environments to treat phobias and post-traumatic stress disorders (PTSD) suggests further exploration of these technologies. Specifically, the augmentation of existing virtual environments with virtual synthetic agents, capable of playing a variety of roles, such as social therapeutic companions for supportive therapies, participants in interactive models of internal dramas or conflicts for psychodynamic therapies, coaches and ‘practice partners’ for cognitive-behavioral therapies, and virtual ‘stand-ins’

/pdf/panel-on-artificial-agents-for-psychotherapy-1g8fry77xt.pdf

Panel on “Artificial Agents for Psychotherapy”

In this demonstration we describe a scenario developed in the EMOTE project. The overall goal of the project is to develop an empathic robot tutor for 11-13 year old school students in an educational setting. We are aiming to develop an empathic robot tutor to teach map reading skills with this scenario on a touch-screen device.

Ana Paiva

Papers

The Dark Side of Embodiment - Teaming Up With Robots VS Disembodied Agents

The user in the group: evaluating the effects of autonomous group dynamics

Learning to be Fair in Multiplayer Ultimatum Games: (Extended Abstract)

Panel on “Artificial Agents for Psychotherapy”

Empathic Robotic Tutors: Map Guide