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

Conflict and conflict dynamics are phenomena intertwined with social change. The ability to detect conflict it is as important as the ability to resolve conflicts effectively because conflicts can bring attention to the problematic structures in a society. In multi-agent systems (MAS), a great deal of work has been devoted to conflict resolution, but little has been discussed regarding detection or creation of conflicts. In this paper, we argue that these processes are central to the agent's decision-making process and should be explicit in an agents' emotional architecture. Our position is that conflict is at the core of any social interaction. Therefore, we adopt a more natural approach by articulating insights from the social sciences literature to define an explicit model of conflict using an emotional architecture of agents and considering theory-of-mind reasoning. Emotions are central to conflict and its experience; hence, conflict is a dynamic process in which emotions are responsible for activating or deactivating it in a conflict loop. In a simulation of a defined scenario scenario, we become aware of the appraisal processes that are activated when the agents are subjected to conflicts, which fit well with our model of the phenomenon.

Conflict inside out: a theoretical approach to conflict from an agent point of view

In this paper we present a study with an autonomous robot that plays a game against a participant, while expressing some social behaviors. We tried to explore the role of emotional sharing from the robot to the user, in order to understand how it might affect the perception of the robot by its users. To study this, two different conditions were formulated: 1-Sharing Condition (the robot shared its emotional state at the end of each board game); and 2-No Sharing Condition (the robot did not shared its emotions). Participants were randomly assigned to one of the conditions and this study followed a between-subject design methodology. It was expected that in the Sharing Condition participants would feel closer to the robot and would perceive/evaluate it as more humanlike. But results contradicted this expectation and called our attention for the caution that needs to exist when building social behaviours to implement in human-robot interactions (HRI).

More Social and Emotional Behaviour May Lead to Poorer Perceptions of a Social Robot

We discuss work carried out at the University of Salford (UK) and INESC-id (Portugal) on the design and implementation of interactive dramas in 3D graphics environments. We present detailed requirements and methods for the design of unscripted (emergent) dramas based on research into role-playing games. We describe the affectively driven intelligent autonomous characters implemented and discuss both theoretical and technical issues relating to its computational implementation. Finally we consider the implications for game design and new genres of game.

Unscripted narrative for affectively driven characters

Understanding how to design agents that sustain cooperation in multi-agent systems has been a long lasting goal in distributed Artificial Intelligence. Solutions proposed rely on identifying defective agents and avoid cooperating or interacting with them. These mechanisms of social control are traditionally studied in games with linear and deterministic payoffs, such as the Prisoner's Dilemma or the Public Goods Game. In reality, however, agents often face dilemmas in which payoffs are uncertain and non-linear, as collective success requires a minimum number of cooperators. These games are called Collective Risk Dilemmas (CRD), and it is unclear whether the previous mechanisms of cooperation remain effective in this case. Here we study cooperation in CRD through partner-based selection. First, we discuss an experiment in which groups of humans and robots play a CRD. We find that people only prefer cooperative partners when they lose a previous game i.e., when collective success was not previously achieved). Secondly, we develop a simplified evolutionary game theoretical model that sheds light on these results, pointing the evolutionary advantages of selecting cooperative partners only when a previous game was lost. We show that this strategy constitutes a convenient balance between strictness (only interact with cooperators) and softness (cooperate and interact with everyone), thus suggesting a new way of designing agents that promote cooperation in CRD.

Outcome-based Partner Selection in Collective Risk Dilemmas

Visually impaired children (VI) face challenges in collaborative learning in classrooms. Robots have the potential to support inclusive classroom experiences by leveraging their physicality, bespoke social behaviors, sensors, and multimodal feedback. However, the design of social robots for mixed-visual abilities classrooms remains mostly unexplored. This paper presents a four-month-long community-based design process where we engaged with a school community. We provide insights into the barriers experienced by children and how social robots can address them. We also report on a participatory design activity with mixed-visual abilities children, highlighting the expected roles, attitudes, and physical characteristics of robots. Findings contextualize social robots within inclusive classroom settings as a holistic solution that can interact anywhere when needed and suggest a broader view of inclusion beyond disability. These include children’s personality traits, technology access, and mastery of school subjects. We finish by providing reflections on the community-based design process.

https://dl.acm.org/doi/pdf/10.1145/3411764.3445135

Ana Paiva

Papers

Conflict inside out: a theoretical approach to conflict from an agent point of view

More Social and Emotional Behaviour May Lead to Poorer Perceptions of a Social Robot

Unscripted narrative for affectively driven characters

Outcome-based Partner Selection in Collective Risk Dilemmas

Community Based Robot Design for Classrooms with Mixed Visual Abilities Children