Due to the vast amount of user-generated content in the emerging Web 2.0, there is a growing need for computational processing of sentiment analysis in documents. Most of the current research in this field is devoted to product reviews from websites. Microblogs and social networks pose even a greater challenge to sentiment classification. However, especially marketing and political campaigns leverage from opinions expressed on Twitter or other social communication platforms. The objects of interest in this paper are the presidential candidates of the Republican Party in the USA and their campaign topics. In this paper we introduce the combination of the noun phrases’ frequency and their PMI measure as constraint on aspect extraction. This compensates for sparse phrases receiving a higher score than those composed of high-frequency words. Evaluation shows that the meronymy relationship between politicians and their topics holds and improves accuracy of aspect extraction.

Neuroprosthesis aims to supersede a damaged or degenerated brain caused by accidents or aging by an artificial brain that simulates and thereby restores the impaired brain functions. To replace the real brain, the artificial brain has to simulate the same functions of the real brain, and the simulation has to be conducted in realtime. We have built a large-scale spiking network model of the cerebellum that is composed of more than 100,000 neuron units and acts as a versatile supervised learning machine for spatiotemporal information. We implement it on a graphics processing unit (GPU) to conduct the numerical simulation in realtime owing to the parallel computing capability of GPUs. We propose to use the present model towards neuroprosthesis.

Future robotic systems are expected to transition from tools to teammates , characterized by increasingly autonomous, intelligent robots interacting with humans in a more naturalistic manner, approaching a relationship more akin to human–human teamwork. Given the impact of trust observed in other systems, trust in the robot team member will likely be critical to effective and safe performance. Our thesis for this paper is that trust in a robot team member must be appropriately calibrated rather than simply maximized.  We describe how the human team member’s understanding of the system contributes to trust in human-robot teaming, by evoking mental model theory. We discuss how mental models are related to physical and behavioral characteristics of the robot, on the one hand, and affective and behavioral outcomes, such as trust and system use/disuse/misuse, on the other.  We expand upon our discussion by providing recommendations for best practices in human-robot team research and design and other systems using artificial intelligence.

The paper discusses the issue of trusting, or the active management of trust (Fitzhugh/etal:2011), in human-robot teams. The paper approaches the issue from the viewpoint of asymmetric agency, and social sentience. The assumption is that humans and robots experience reality differently (asymmetry), and that a robot is endowed with an explicit (deliberative) awareness of its role within the team, and of the social dynamics of the team (social sentience). A formal approach is outlined, to provide the basis for a model of trusting in terms of (i) trust in information and how to act upon that (as judgements about actions and interactions, at the task-level), and (ii) the reflection of trust between actors in a team, in how social dynamics get directed over time (team-level). The focus is thus primarily on the integration of trust and its adaptation in the dynamics of collaboration.

Conventional paradigms of machine learning assume all the training data are available when learning starts. However, in lifelong learning, the examples are observed sequentially as learning unfolds, and the learner should continually explore the world and reorganize and refine the internal model or knowledge of the world. This leads to a fundamental challenge: How to balance long-term and short-term goals and how to trade-off between information gain and model complexity? These questions boil down to “what objective functions can best guide a lifelong learning agent?” Here we develop a sequential Bayesian framework for lifelong learning, build a taxonomy of lifelong-learning paradigms, and examine information-theoretic objective functions for each paradigm, with an emphasis on predictive and active learning. The objective functions can provide theoretical criteria for designing algorithms and determining effective strategies for selective sampling, representation discovery, knowledge transfer, and continual update over a lifetime of experience.

The recently developed Efficient Lifelong Learning Algorithm (ELLA) acquires knowledge incrementally over a sequence of tasks, learning a repository of latent model components that are sparsely shared between models. ELLA shows strong performance in comparison to other multi-task learning algorithms, achieving nearly identical performance to batch multi-task learning methods while learning tasks sequentially in three orders of magnitude (over 1,000x) less time. In this paper, we evaluate several curriculum selection methods that allow ELLA to actively select the next task for learning in order to maximize performance on future learning tasks. Through experiments with three real and one synthetic data set, we demonstrate that active curriculum selection allows an agent to learn up to 50% more efficiently than when the agent has no control over the task order.

We address the problem faced by an autonomous agent that must achieve quick responses to a family of qualitatively-related tasks, such as a robot interacting with different types of human participants. We work in the setting where the tasks share a state-action space and have the same qualitative objective but differ in the dynamics and reward process. We adopt a transfer approach where the agent attempts to exploit common structure in learnt policies to accelerate learning in a new one. Our technique consists of a few key steps. First, we use a probabilistic model to describe the regions in state space which successful trajectories seem to prefer. Then, we extract policy fragments from previously-learnt policies for these regions as candidates for reuse. These fragments may be treated as options with corresponding domains and termination conditions extracted by unsupervised learning. Then, the set of reusable policies is used when learning novel tasks, and the process repeats. The utility of this method is demonstrated through experiments in the simulated soccer domain, where the variability comes from the different possible behaviours of opponent teams, and the agent needs to perform well against novel opponents.

In many real-life design problems, there is a requirement to simultaneously balance multiple tasks or objectives in the system that are conflicting in nature, where minimizing one objective causes another to increase in value, thereby resulting in trade-offs between the objectives. For example, in embedded multi-core mobile devices and very large scale data centers, there is a continuous problem of simultaneously balancing interfering goals of maximal power savings and minimal performance delay with varying trade-off values for different application workloads executing on them. Typically, the optimal trade-offs for the executing workloads, lie on a difficult to determine optimal Pareto front. The nature of the problem requires learning over the lifetime of the mobile device or server with continuous evaluation and prediction of the trade-off settings on the system that balances the interfering objectives optimally. Towards this, we propose an on-line learning method, where the weights of experts for addressing the objectives are updated based on a convex combination of their relative performance in addressing all objectives simultaneously. An additional importance vector that assigns relative importance to each objective at every round is used, and is sampled from a convex cone pointed at the origin Our preliminary results show that the convex combination of the importance vector and the gradient of the potential functions of the learner's regret with respect to each objective ensure that in the next round, the drift (instantaneous regret vector), is the Pareto descent direction that enables better convergence to the optimal Pareto front.

We describe an approach for multi-engine machine translation that uses machine learning methods to train one or several classifiers for a given set of candidate translations. Contrary to existing approaches in quality estimation which only consider a single translation at a time, we explicitly model pairwise comparison with our feature vectors. We discuss several challenges our method is facing and discuss how lifelong machine learning could be applied to resolve these. We also show how the proposed architecture can be extended to allow human feedback to be included into the training process, improving the system's selection process over time.

Facing the fourth industrial revolution, autonomous mobile robots are expected to play an important role in the production processes of the future. The new Logistics League Sponsored by Festo (LLSF) under the RoboCup umbrella focuses on this aspect of robotics to provide a benchmark testbed on a common robot platform. We describe certain aspects of the integrated robot system of our Carologistics RoboCup team, in particular our reasoning system for the supply chain problem of the LLSF. We approach the problem by deploying the CLIPS rules engine for product planning and dealing with the incomplete knowledge that exists in the domain and show that it is suitable for computationally limited platforms.