Modelling shared attention through relational reinforcement learning

Shared attention is a type of communication very important among human beings. It is sometimes reserved for the more complex form of communication being constituted by a sequence of four steps: mutual gaze, gaze following, imperative pointing and declarative pointing. Some approaches have been proposed in Human-Robot Interaction area to solve part of shared attention process, that is, the most of works proposed try to solve the first two steps. Models based on temporal difference, neural networks, probabilistic and reinforcement learning are methods used in several works. In this article, we are presenting a robotic architecture that provides a robot or agent, the capacity of learning mutual gaze, gaze following and declarative pointing using a robotic head interacting with a caregiver. Three learning methods have been incorporated to this architecture and a comparison of their performance has been done to find the most adequate to be used in real experiment. The learning capabilities of this architecture have been analyzed by observing the robot interacting with the human in a controlled environment. The experimental results show that the robotic head is able to produce appropriate behavior and to learn from sociable interaction.

Semi-supervised learning guided by the modularity measure in complex networks

Semi-supervised learning techniques have gained increasing attention in the machine learning community, as a result of two main factors: (1) the available data is exponentially increasing; (2) the task of data labeling is cumbersome and expensive, involving human experts in the process. In this paper, we propose a network-based semi-supervised learning method inspired by the modularity greedy algorithm, which was originally applied for unsupervised learning. Changes have been made in the process of modularity maximization in a way to adapt the model to propagate labels throughout the network. Furthermore, a network reduction technique is introduced, as well as an extensive analysis of its impact on the network. Computer simulations are performed for artificial and real-world databases, providing a numerical quantitative basis for the performance of the proposed method.

Motor learning, retention and transfer after virtual-reality-based training in Parkinson's disease - effect of motor and cognitive demands of games: a longitudinal, controlled clinical study

Objectives To evaluate the learning, retention and transfer of performance improvements after Nintendo Wii Fit (TM) training in patients with Parkinson's disease and healthy elderly people. Design Longitudinal, controlled clinical study. Participants Sixteen patients with early-stage Parkinson's disease and 11 healthy elderly people. Interventions Warm-up exercises and Wii Fit training that involved training motor (shifts centre of gravity and step alternation) and cognitive skills. A follow-up evaluative Wii Fit session was held 60 days after the end of training. Participants performed a functional reach test before and after training as a measure of learning transfer. Main outcome measures Learning and retention were determined based on the scores of 10 Wii Fit games over eight sessions. Transfer of learning was assessed after training using the functional reach test. Results Patients with Parkinson's disease showed no deficit in learning or retention on seven of the 10 games, despite showing poorer performance on five games compared with the healthy elderly group. Patients with Parkinson's disease showed marked learning deficits on three other games, independent of poorer initial performance. This deficit appears to be associated with cognitive demands of the games which require decision-making, response inhibition, divided attention and working memory. Finally, patients with Parkinson's disease were able to transfer motor ability trained on the games to a similar untrained task. Conclusions The ability of patients with Parkinson's disease to learn, retain and transfer performance improvements after training on the Nintendo Wii Fit depends largely on the demands, particularly cognitive demands, of the games involved, reiterating the importance of game selection for rehabilitation purposes. (C) 2012 Chartered Society of Physiotherapy. Published by Elsevier Ltd. All rights reserved.

Bias and learning in temporal binding: intervals between actions and outcomes are compressed by prior bias

It has consistently been shown that agents judge the intervals between their actions and outcomes as compressed in time, an effect named intentional binding. In the present work, we investigated whether this effect is result of prior bias volunteers have about the timing of the consequences of their actions, or if it is due to learning that occurs during the experimental session. Volunteers made temporal estimates of the interval between their action and target onset (Action conditions), or between two events (No-Action conditions). Our results show that temporal estimates become shorter throughout each experimental block in both conditions. Moreover, we found that observers judged intervals between action and outcomes as shorter even in very early trials of each block. To quantify the decrease of temporal judgments in experimental blocks, exponential functions were fitted to participants’ temporal judgments. The fitted parameters suggest that observers had different prior biases as to intervals between events in which action was involved. These findings suggest that prior bias might play a more important role in this effect than calibration-type learning processes.