Classification-based reinforcement learning (RL) methods have recently been proposed as an alternative to the traditional value-function based methods. These methods use a classifier to represent a policy, where the input (features) to the classifier is the state and the output (class label) for that state is the desired action. The reinforcement-learning community knows that focusing on more i...

Estimating the wandering visual focus of attention (WVFOA) for multiple people is an important problem with many applications in human behavior understanding. One such application, addressed in this paper, monitors the attention of passers-by to outdoor advertisements. To solve the WVFOA problem, we propose a multi-person tracking approach based on a hybrid Dynamic Bayesian Network that simulta...

We present a method to stop the evaluation of a prediction process when the result of the full evaluation is obvious. This trait is highly desirable in prediction tasks where a predictor evaluates all its features for every example in large datasets. We observe that some examples are easier to classify than others, a phenomenon which is characterized by the event when most of the features agree...

The significance of the recent introduction to cognitive neuroscience of multivariate pattern analysis (MVPA) is that, unlike univariate approaches which are limited to identifying magnitudes of activity in localized parts of the brain, it affords the detection and characterization of patterns of activity distributed within and across multiple brain regions. This technique supports stronger inf...

We investigate the problem of using function approximation in reinforcement learning (RL) where the agent’s control policy is represented as a classifier mapping states to actions. The innovation of this paper lies with introducing a measure of state’s decision-making importance. We then use an efficient approximation to this measure as misclassification costs in learning the agent’s policy. As...

Walker (1996) presents a cache model of the operation of attention in the processing of discourse as an alternative to the focus space stack that was proposed previously by Grosz and Sidner (Grosz 1977a; Grosz and Sidner 1986). In this squib, we present a critical analysis of the cache model and of Walker's supporting evidence from anaphora in discourses with interruptions and from informationa...

We present a method to stop the evaluation of a decision making process when the result of the full evaluation is obvious. This trait is highly desirable for online marginbased machine learning algorithms where a classifier traditionally evaluates all the features for every example. We observe that some examples are easier to classify than others, a phenomenon which is characterized by the even...

A series of 4 experiments were conducted to investigate ideational productivity. Experiments 1, 2, and 3 were carried out under controlled conditions and involved a test of ideational productivity based on producing different interpretations of a diagram. In the first experiment, the pattern of ideational productivity of adult volunteer participants was studied over 30 min of thinking time. Exp...

Identifying human gaze or eye-movement ultimately serves the purpose of identifying an individual's focus of attention. The knowledge of a person's object of interest helps us e ectively communicate with other humans by allowing us to identify our conversants' interests, state of mind, and/or intentions. In this paper we propose to track focus of attention of several participants in a meeting. ...

In this paper, we argue that natural language interfaces with discourse capabilities have an important role to play in decision support systems, because such interfaces are responsive to focus of attention in the mind of a human decision maker. The decision support systems that we will discuss employ graphical user interfaces. They are characterized by strict ordering requirements for commands,...